summaryrefslogtreecommitdiffstats
path: root/Lib/mimetypes.py
blob: 4c054c961cd71550d8f299b9a01b806e8e4e434c (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
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
"""Guess the MIME type of a file.

This module defines two useful functions:

guess_type(url, strict=1) -- guess the MIME type and encoding of a URL.

guess_extension(type, strict=1) -- guess the extension for a given MIME type.

It also contains the following, for tuning the behavior:

Data:

knownfiles -- list of files to parse
inited -- flag set when init() has been called
suffix_map -- dictionary mapping suffixes to suffixes
encodings_map -- dictionary mapping suffixes to encodings
types_map -- dictionary mapping suffixes to types

Functions:

init([files]) -- parse a list of files, default knownfiles (on Windows, the
  default values are taken from the registry)
read_mime_types(file) -- parse one file, return a dictionary or None
"""

import os
import sys
import posixpath
import urllib
try:
    import _winreg
except ImportError:
    _winreg = None

__all__ = [
    "guess_type","guess_extension","guess_all_extensions",
    "add_type","read_mime_types","init"
]

knownfiles = [
    "/etc/mime.types",
    "/etc/httpd/mime.types",                    # Mac OS X
    "/etc/httpd/conf/mime.types",               # Apache
    "/etc/apache/mime.types",                   # Apache 1
    "/etc/apache2/mime.types",                  # Apache 2
    "/usr/local/etc/httpd/conf/mime.types",
    "/usr/local/lib/netscape/mime.types",
    "/usr/local/etc/httpd/conf/mime.types",     # Apache 1.2
    "/usr/local/etc/mime.types",                # Apache 1.3
    ]

inited = False
_db = None


class MimeTypes:
    """MIME-types datastore.

    This datastore can handle information from mime.types-style files
    and supports basic determination of MIME type from a filename or
    URL, and can guess a reasonable extension given a MIME type.
    """

    def __init__(self, filenames=(), strict=True):
        if not inited:
            init()
        self.encodings_map = encodings_map.copy()
        self.suffix_map = suffix_map.copy()
        self.types_map = ({}, {}) # dict for (non-strict, strict)
        self.types_map_inv = ({}, {})
        for (ext, type) in types_map.items():
            self.add_type(type, ext, True)
        for (ext, type) in common_types.items():
            self.add_type(type, ext, False)
        for name in filenames:
            self.read(name, strict)

    def add_type(self, type, ext, strict=True):
        """Add a mapping between a type and an extension.

        When the extension is already known, the new
        type will replace the old one. When the type
        is already known the extension will be added
        to the list of known extensions.

        If strict is true, information will be added to
        list of standard types, else to the list of non-standard
        types.
        """
        self.types_map[strict][ext] = type
        exts = self.types_map_inv[strict].setdefault(type, [])
        if ext not in exts:
            exts.append(ext)

    def guess_type(self, url, strict=True):
        """Guess the type of a file based on its URL.

        Return value is a tuple (type, encoding) where type is None if
        the type can't be guessed (no or unknown suffix) or a string
        of the form type/subtype, usable for a MIME Content-type
        header; and encoding is None for no encoding or the name of
        the program used to encode (e.g. compress or gzip).  The
        mappings are table driven.  Encoding suffixes are case
        sensitive; type suffixes are first tried case sensitive, then
        case insensitive.

        The suffixes .tgz, .taz and .tz (case sensitive!) are all
        mapped to '.tar.gz'.  (This is table-driven too, using the
        dictionary suffix_map.)

        Optional `strict' argument when False adds a bunch of commonly found,
        but non-standard types.
        """
        scheme, url = urllib.splittype(url)
        if scheme == 'data':
            # syntax of data URLs:
            # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
            # mediatype := [ type "/" subtype ] *( ";" parameter )
            # data      := *urlchar
            # parameter := attribute "=" value
            # type/subtype defaults to "text/plain"
            comma = url.find(',')
            if comma < 0:
                # bad data URL
                return None, None
            semi = url.find(';', 0, comma)
            if semi >= 0:
                type = url[:semi]
            else:
                type = url[:comma]
            if '=' in type or '/' not in type:
                type = 'text/plain'
            return type, None           # never compressed, so encoding is None
        base, ext = posixpath.splitext(url)
        while ext in self.suffix_map:
            base, ext = posixpath.splitext(base + self.suffix_map[ext])
        if ext in self.encodings_map:
            encoding = self.encodings_map[ext]
            base, ext = posixpath.splitext(base)
        else:
            encoding = None
        types_map = self.types_map[True]
        if ext in types_map:
            return types_map[ext], encoding
        elif ext.lower() in types_map:
            return types_map[ext.lower()], encoding
        elif strict:
            return None, encoding
        types_map = self.types_map[False]
        if ext in types_map:
            return types_map[ext], encoding
        elif ext.lower() in types_map:
            return types_map[ext.lower()], encoding
        else:
            return None, encoding

    def guess_all_extensions(self, type, strict=True):
        """Guess the extensions for a file based on its MIME type.

        Return value is a list of strings giving the possible filename
        extensions, including the leading dot ('.').  The extension is not
        guaranteed to have been associated with any particular data stream,
        but would be mapped to the MIME type `type' by guess_type().

        Optional `strict' argument when false adds a bunch of commonly found,
        but non-standard types.
        """
        type = type.lower()
        extensions = self.types_map_inv[True].get(type, [])
        if not strict:
            for ext in self.types_map_inv[False].get(type, []):
                if ext not in extensions:
                    extensions.append(ext)
        return extensions

    def guess_extension(self, type, strict=True):
        """Guess the extension for a file based on its MIME type.

        Return value is a string giving a filename extension,
        including the leading dot ('.').  The extension is not
        guaranteed to have been associated with any particular data
        stream, but would be mapped to the MIME type `type' by
        guess_type().  If no extension can be guessed for `type', None
        is returned.

        Optional `strict' argument when false adds a bunch of commonly found,
        but non-standard types.
        """
        extensions = self.guess_all_extensions(type, strict)
        if not extensions:
            return None
        return extensions[0]

    def read(self, filename, strict=True):
        """
        Read a single mime.types-format file, specified by pathname.

        If strict is true, information will be added to
        list of standard types, else to the list of non-standard
        types.
        """
        with open(filename) as fp:
            self.readfp(fp, strict)

    def readfp(self, fp, strict=True):
        """
        Read a single mime.types-format file.

        If strict is true, information will be added to
        list of standard types, else to the list of non-standard
        types.
        """
        while 1:
            line = fp.readline()
            if not line:
                break
            words = line.split()
            for i in range(len(words)):
                if words[i][0] == '#':
                    del words[i:]
                    break
            if not words:
                continue
            type, suffixes = words[0], words[1:]
            for suff in suffixes:
                self.add_type(type, '.' + suff, strict)

    def read_windows_registry(self, strict=True):
        """
        Load the MIME types database from Windows registry.

        If strict is true, information will be added to
        list of standard types, else to the list of non-standard
        types.
        """

        # Windows only
        if not _winreg:
            return

        def enum_types(mimedb):
            i = 0
            while True:
                try:
                    ctype = _winreg.EnumKey(mimedb, i)
                except EnvironmentError:
                    break
                try:
                    ctype = ctype.encode(default_encoding) # omit in 3.x!
                except UnicodeEncodeError:
                    pass
                else:
                    yield ctype
                i += 1

        default_encoding = sys.getdefaultencoding()
        with _winreg.OpenKey(_winreg.HKEY_CLASSES_ROOT,
                             r'MIME\Database\Content Type') as mimedb:
            for ctype in enum_types(mimedb):
                try:
                    with _winreg.OpenKey(mimedb, ctype) as key:
                        suffix, datatype = _winreg.QueryValueEx(key,
                                                                'Extension')
                except EnvironmentError:
                    continue
                if datatype != _winreg.REG_SZ:
                    continue
                try:
                    suffix = suffix.encode(default_encoding) # omit in 3.x!
                except UnicodeEncodeError:
                    continue
                self.add_type(ctype, suffix, strict)


def guess_type(url, strict=True):
    """Guess the type of a file based on its URL.

    Return value is a tuple (type, encoding) where type is None if the
    type can't be guessed (no or unknown suffix) or a string of the
    form type/subtype, usable for a MIME Content-type header; and
    encoding is None for no encoding or the name of the program used
    to encode (e.g. compress or gzip).  The mappings are table
    driven.  Encoding suffixes are case sensitive; type suffixes are
    first tried case sensitive, then case insensitive.

    The suffixes .tgz, .taz and .tz (case sensitive!) are all mapped
    to ".tar.gz".  (This is table-driven too, using the dictionary
    suffix_map).

    Optional `strict' argument when false adds a bunch of commonly found, but
    non-standard types.
    """
    if _db is None:
        init()
    return _db.guess_type(url, strict)


def guess_all_extensions(type, strict=True):
    """Guess the extensions for a file based on its MIME type.

    Return value is a list of strings giving the possible filename
    extensions, including the leading dot ('.').  The extension is not
    guaranteed to have been associated with any particular data
    stream, but would be mapped to the MIME type `type' by
    guess_type().  If no extension can be guessed for `type', None
    is returned.

    Optional `strict' argument when false adds a bunch of commonly found,
    but non-standard types.
    """
    if _db is None:
        init()
    return _db.guess_all_extensions(type, strict)

def guess_extension(type, strict=True):
    """Guess the extension for a file based on its MIME type.

    Return value is a string giving a filename extension, including the
    leading dot ('.').  The extension is not guaranteed to have been
    associated with any particular data stream, but would be mapped to the
    MIME type `type' by guess_type().  If no extension can be guessed for
    `type', None is returned.

    Optional `strict' argument when false adds a bunch of commonly found,
    but non-standard types.
    """
    if _db is None:
        init()
    return _db.guess_extension(type, strict)

def add_type(type, ext, strict=True):
    """Add a mapping between a type and an extension.

    When the extension is already known, the new
    type will replace the old one. When the type
    is already known the extension will be added
    to the list of known extensions.

    If strict is true, information will be added to
    list of standard types, else to the list of non-standard
    types.
    """
    if _db is None:
        init()
    return _db.add_type(type, ext, strict)


def init(files=None):
    global suffix_map, types_map, encodings_map, common_types
    global inited, _db
    inited = True    # so that MimeTypes.__init__() doesn't call us again
    db = MimeTypes()
    if files is None:
        if _winreg:
            db.read_windows_registry()
        files = knownfiles
    for file in files:
        if os.path.isfile(file):
            db.read(file)
    encodings_map = db.encodings_map
    suffix_map = db.suffix_map
    types_map = db.types_map[True]
    common_types = db.types_map[False]
    # Make the DB a global variable now that it is fully initialized
    _db = db


def read_mime_types(file):
    try:
        f = open(file)
    except IOError:
        return None
    db = MimeTypes()
    db.readfp(f, True)
    return db.types_map[True]


def _default_mime_types():
    global suffix_map
    global encodings_map
    global types_map
    global common_types

    suffix_map = {
        '.tgz': '.tar.gz',
        '.taz': '.tar.gz',
        '.tz': '.tar.gz',
        '.tbz2': '.tar.bz2',
        }

    encodings_map = {
        '.gz': 'gzip',
        '.Z': 'compress',
        '.bz2': 'bzip2',
        }

    # Before adding new types, make sure they are either registered with IANA,
    # at http://www.isi.edu/in-notes/iana/assignments/media-types
    # or extensions, i.e. using the x- prefix

    # If you add to these, please keep them sorted!
    types_map = {
        '.a'      : 'application/octet-stream',
        '.ai'     : 'application/postscript',
        '.aif'    : 'audio/x-aiff',
        '.aifc'   : 'audio/x-aiff',
        '.aiff'   : 'audio/x-aiff',
        '.au'     : 'audio/basic',
        '.avi'    : 'video/x-msvideo',
        '.bat'    : 'text/plain',
        '.bcpio'  : 'application/x-bcpio',
        '.bin'    : 'application/octet-stream',
        '.bmp'    : 'image/x-ms-bmp',
        '.c'      : 'text/plain',
        # Duplicates :(
        '.cdf'    : 'application/x-cdf',
        '.cdf'    : 'application/x-netcdf',
        '.cpio'   : 'application/x-cpio',
        '.csh'    : 'application/x-csh',
        '.css'    : 'text/css',
        '.dll'    : 'application/octet-stream',
        '.doc'    : 'application/msword',
        '.dot'    : 'application/msword',
        '.dvi'    : 'application/x-dvi',
        '.eml'    : 'message/rfc822',
        '.eps'    : 'application/postscript',
        '.etx'    : 'text/x-setext',
        '.exe'    : 'application/octet-stream',
        '.gif'    : 'image/gif',
        '.gtar'   : 'application/x-gtar',
        '.h'      : 'text/plain',
        '.hdf'    : 'application/x-hdf',
        '.htm'    : 'text/html',
        '.html'   : 'text/html',
        '.ief'    : 'image/ief',
        '.jpe'    : 'image/jpeg',
        '.jpeg'   : 'image/jpeg',
        '.jpg'    : 'image/jpeg',
        '.js'     : 'application/x-javascript',
        '.ksh'    : 'text/plain',
        '.latex'  : 'application/x-latex',
        '.m1v'    : 'video/mpeg',
        '.man'    : 'application/x-troff-man',
        '.me'     : 'application/x-troff-me',
        '.mht'    : 'message/rfc822',
        '.mhtml'  : 'message/rfc822',
        '.mif'    : 'application/x-mif',
        '.mov'    : 'video/quicktime',
        '.movie'  : 'video/x-sgi-movie',
        '.mp2'    : 'audio/mpeg',
        '.mp3'    : 'audio/mpeg',
        '.mp4'    : 'video/mp4',
        '.mpa'    : 'video/mpeg',
        '.mpe'    : 'video/mpeg',
        '.mpeg'   : 'video/mpeg',
        '.mpg'    : 'video/mpeg',
        '.ms'     : 'application/x-troff-ms',
        '.nc'     : 'application/x-netcdf',
        '.nws'    : 'message/rfc822',
        '.o'      : 'application/octet-stream',
        '.obj'    : 'application/octet-stream',
        '.oda'    : 'application/oda',
        '.p12'    : 'application/x-pkcs12',
        '.p7c'    : 'application/pkcs7-mime',
        '.pbm'    : 'image/x-portable-bitmap',
        '.pdf'    : 'application/pdf',
        '.pfx'    : 'application/x-pkcs12',
        '.pgm'    : 'image/x-portable-graymap',
        '.pl'     : 'text/plain',
        '.png'    : 'image/png',
        '.pnm'    : 'image/x-portable-anymap',
        '.pot'    : 'application/vnd.ms-powerpoint',
        '.ppa'    : 'application/vnd.ms-powerpoint',
        '.ppm'    : 'image/x-portable-pixmap',
        '.pps'    : 'application/vnd.ms-powerpoint',
        '.ppt'    : 'application/vnd.ms-powerpoint',
        '.ps'     : 'application/postscript',
        '.pwz'    : 'application/vnd.ms-powerpoint',
        '.py'     : 'text/x-python',
        '.pyc'    : 'application/x-python-code',
        '.pyo'    : 'application/x-python-code',
        '.qt'     : 'video/quicktime',
        '.ra'     : 'audio/x-pn-realaudio',
        '.ram'    : 'application/x-pn-realaudio',
        '.ras'    : 'image/x-cmu-raster',
        '.rdf'    : 'application/xml',
        '.rgb'    : 'image/x-rgb',
        '.roff'   : 'application/x-troff',
        '.rtx'    : 'text/richtext',
        '.sgm'    : 'text/x-sgml',
        '.sgml'   : 'text/x-sgml',
        '.sh'     : 'application/x-sh',
        '.shar'   : 'application/x-shar',
        '.snd'    : 'audio/basic',
        '.so'     : 'application/octet-stream',
        '.src'    : 'application/x-wais-source',
        '.sv4cpio': 'application/x-sv4cpio',
        '.sv4crc' : 'application/x-sv4crc',
        '.swf'    : 'application/x-shockwave-flash',
        '.t'      : 'application/x-troff',
        '.tar'    : 'application/x-tar',
        '.tcl'    : 'application/x-tcl',
        '.tex'    : 'application/x-tex',
        '.texi'   : 'application/x-texinfo',
        '.texinfo': 'application/x-texinfo',
        '.tif'    : 'image/tiff',
        '.tiff'   : 'image/tiff',
        '.tr'     : 'application/x-troff',
        '.tsv'    : 'text/tab-separated-values',
        '.txt'    : 'text/plain',
        '.ustar'  : 'application/x-ustar',
        '.vcf'    : 'text/x-vcard',
        '.wav'    : 'audio/x-wav',
        '.wiz'    : 'application/msword',
        '.wsdl'   : 'application/xml',
        '.xbm'    : 'image/x-xbitmap',
        '.xlb'    : 'application/vnd.ms-excel',
        # Duplicates :(
        '.xls'    : 'application/excel',
        '.xls'    : 'application/vnd.ms-excel',
        '.xml'    : 'text/xml',
        '.xpdl'   : 'application/xml',
        '.xpm'    : 'image/x-xpixmap',
        '.xsl'    : 'application/xml',
        '.xwd'    : 'image/x-xwindowdump',
        '.zip'    : 'application/zip',
        }

    # These are non-standard types, commonly found in the wild.  They will
    # only match if strict=0 flag is given to the API methods.

    # Please sort these too
    common_types = {
        '.jpg' : 'image/jpg',
        '.mid' : 'audio/midi',
        '.midi': 'audio/midi',
        '.pct' : 'image/pict',
        '.pic' : 'image/pict',
        '.pict': 'image/pict',
        '.rtf' : 'application/rtf',
        '.xul' : 'text/xul'
        }


_default_mime_types()


if __name__ == '__main__':
    import getopt

    USAGE = """\
Usage: mimetypes.py [options] type

Options:
    --help / -h       -- print this message and exit
    --lenient / -l    -- additionally search of some common, but non-standard
                         types.
    --extension / -e  -- guess extension instead of type

More than one type argument may be given.
"""

    def usage(code, msg=''):
        print USAGE
        if msg: print msg
        sys.exit(code)

    try:
        opts, args = getopt.getopt(sys.argv[1:], 'hle',
                                   ['help', 'lenient', 'extension'])
    except getopt.error, msg:
        usage(1, msg)

    strict = 1
    extension = 0
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-l', '--lenient'):
            strict = 0
        elif opt in ('-e', '--extension'):
            extension = 1
    for gtype in args:
        if extension:
            guess = guess_extension(gtype, strict)
            if not guess: print "I don't know anything about type", gtype
            else: print guess
        else:
            guess, encoding = guess_type(gtype, strict)
            if not guess: print "I don't know anything about type", gtype
            else: print 'type:', guess, 'encoding:', encoding