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

"""MIME-Type Parser

This module provides basic functions for handling mime-types. It can handle
matching mime-types against a list of media-ranges. See section 14.1 of 
the HTTP specification [RFC 2616] for a complete explanation.

   http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.1

Contents:
    - parse_mime_type():   Parses a mime-type into its component parts.
    - parse_media_range(): Media-ranges are mime-types with wild-cards and a 'q' quality parameter.
    - quality():           Determines the quality ('q') of a mime-type when compared against a list of media-ranges.
    - quality_parsed():    Just like quality() except the second parameter must be pre-parsed.
    - best_match():        Choose the mime-type with the highest quality ('q') from a list of candidates. 
"""

__version__ = "0.1.2"
__author__ = 'Joe Gregorio'
__email__ = "joe@bitworking.org"
__credits__ = ""

def parse_mime_type(mime_type):
    """Carves up a mime-type and returns a tuple of the
       (type, subtype, params) where 'params' is a dictionary
       of all the parameters for the media range.
       For example, the media range 'application/xhtml;q=0.5' would
       get parsed into:

       ('application', 'xhtml', {'q', '0.5'})
       """
    parts = mime_type.split(";")
    params = dict([tuple([s.strip() for s in param.split("=")])\
            for param in parts[1:] ])
    full_type = parts[0].strip()
    # Java URLConnection class sends an Accept header that includes a single "*"
    # Turn it into a legal wildcard.
    if full_type == '*': full_type = '*/*'
    (type, subtype) = full_type.split("/")
    return (type.strip(), subtype.strip(), params)

def parse_media_range(range):
    """Carves up a media range and returns a tuple of the
       (type, subtype, params) where 'params' is a dictionary
       of all the parameters for the media range.
       For example, the media range 'application/*;q=0.5' would
       get parsed into:

       ('application', '*', {'q', '0.5'})

       In addition this function also guarantees that there 
       is a value for 'q' in the params dictionary, filling it
       in with a proper default if necessary.
       """
    (type, subtype, params) = parse_mime_type(range)
    if not params.has_key('q') or not params['q'] or \
            not float(params['q']) or float(params['q']) > 1\
            or float(params['q']) < 0:
        params['q'] = '1'
    return (type, subtype, params)

def fitness_and_quality_parsed(mime_type, parsed_ranges):
    """Find the best match for a given mime-type against 
       a list of media_ranges that have already been 
       parsed by parse_media_range(). Returns a tuple of
       the fitness value and the value of the 'q' quality
       parameter of the best match, or (-1, 0) if no match
       was found. Just as for quality_parsed(), 'parsed_ranges'
       must be a list of parsed media ranges. """
    best_fitness = -1 
    best_fit_q = 0
    (target_type, target_subtype, target_params) =\
            parse_media_range(mime_type)
    for (type, subtype, params) in parsed_ranges:
        if (type == target_type or type == '*' or target_type == '*') and \
                (subtype == target_subtype or subtype == '*' or target_subtype == '*'):
            param_matches = reduce(lambda x, y: x+y, [1 for (key, value) in \
                    target_params.iteritems() if key != 'q' and \
                    params.has_key(key) and value == params[key]], 0)
            fitness = (type == target_type) and 100 or 0
            fitness += (subtype == target_subtype) and 10 or 0
            fitness += param_matches
            if fitness > best_fitness:
                best_fitness = fitness
                best_fit_q = params['q']
            
    return best_fitness, float(best_fit_q)

def quality_parsed(mime_type, parsed_ranges):
    """Find the best match for a given mime-type against
    a list of media_ranges that have already been
    parsed by parse_media_range(). Returns the
    'q' quality parameter of the best match, 0 if no
    match was found. This function bahaves the same as quality()
    except that 'parsed_ranges' must be a list of
    parsed media ranges. """
    return fitness_and_quality_parsed(mime_type, parsed_ranges)[1]

def quality(mime_type, ranges):
    """Returns the quality 'q' of a mime-type when compared
    against the media-ranges in ranges. For example:

    >>> quality('text/html','text/*;q=0.3, text/html;q=0.7, text/html;level=1, text/html;level=2;q=0.4, */*;q=0.5')
    0.7
    
    """ 
    parsed_ranges = [parse_media_range(r) for r in ranges.split(",")]
    return quality_parsed(mime_type, parsed_ranges)

def best_match(supported, header):
    """Takes a list of supported mime-types and finds the best
    match for all the media-ranges listed in header. The value of
    header must be a string that conforms to the format of the 
    HTTP Accept: header. The value of 'supported' is a list of
    mime-types.
    
    >>> best_match(['application/xbel+xml', 'text/xml'], 'text/*;q=0.5,*/*; q=0.1')
    'text/xml'
    """
    parsed_header = [parse_media_range(r) for r in header.split(",")]
    weighted_matches = [(fitness_and_quality_parsed(mime_type, parsed_header), mime_type)\
            for mime_type in supported]
    weighted_matches.sort()
    return weighted_matches[-1][0][1] and weighted_matches[-1][1] or ''

if __name__ == "__main__":
    import unittest

    class TestMimeParsing(unittest.TestCase):

        def test_parse_media_range(self):
            self.assert_(('application', 'xml', {'q': '1'}) == parse_media_range('application/xml;q=1'))
            self.assertEqual(('application', 'xml', {'q': '1'}), parse_media_range('application/xml'))
            self.assertEqual(('application', 'xml', {'q': '1'}), parse_media_range('application/xml;q='))
            self.assertEqual(('application', 'xml', {'q': '1'}), parse_media_range('application/xml ; q='))
            self.assertEqual(('application', 'xml', {'q': '1', 'b': 'other'}), parse_media_range('application/xml ; q=1;b=other'))
            self.assertEqual(('application', 'xml', {'q': '1', 'b': 'other'}), parse_media_range('application/xml ; q=2;b=other'))
            # Java URLConnection class sends an Accept header that includes a single *
            self.assertEqual(('*', '*', {'q': '.2'}), parse_media_range(" *; q=.2"))

        def test_rfc_2616_example(self):
            accept = "text/*;q=0.3, text/html;q=0.7, text/html;level=1, text/html;level=2;q=0.4, */*;q=0.5"
            self.assertEqual(1, quality("text/html;level=1", accept))
            self.assertEqual(0.7, quality("text/html", accept))
            self.assertEqual(0.3, quality("text/plain", accept))
            self.assertEqual(0.5, quality("image/jpeg", accept))
            self.assertEqual(0.4, quality("text/html;level=2", accept))
            self.assertEqual(0.7, quality("text/html;level=3", accept))

        def test_best_match(self):
            mime_types_supported = ['application/xbel+xml', 'application/xml']
            # direct match
            self.assertEqual(best_match(mime_types_supported, 'application/xbel+xml'), 'application/xbel+xml')
            # direct match with a q parameter
            self.assertEqual(best_match(mime_types_supported, 'application/xbel+xml; q=1'), 'application/xbel+xml')
            # direct match of our second choice with a q parameter
            self.assertEqual(best_match(mime_types_supported, 'application/xml; q=1'), 'application/xml')
            # match using a subtype wildcard
            self.assertEqual(best_match(mime_types_supported, 'application/*; q=1'), 'application/xml')
            # match using a type wildcard
            self.assertEqual(best_match(mime_types_supported, '*/*'), 'application/xml')

            mime_types_supported = ['application/xbel+xml', 'text/xml']
            # match using a type versus a lower weighted subtype
            self.assertEqual(best_match(mime_types_supported, 'text/*;q=0.5,*/*; q=0.1'), 'text/xml')
            # fail to match anything
            self.assertEqual(best_match(mime_types_supported, 'text/html,application/atom+xml; q=0.9'), '')

            # common AJAX scenario
            mime_types_supported = ['application/json', 'text/html']
            self.assertEqual(best_match(mime_types_supported, 'application/json, text/javascript, */*'), 'application/json')
            # verify fitness ordering
            self.assertEqual(best_match(mime_types_supported, 'application/json, text/html;q=0.9'), 'application/json')

        def test_support_wildcards(self):
            mime_types_supported = ['image/*', 'application/xml']
            # match using a type wildcard
            self.assertEqual(best_match(mime_types_supported, 'image/png'), 'image/*')
            # match using a wildcard for both requested and supported 
            self.assertEqual(best_match(mime_types_supported, 'image/*'), 'image/*')

    unittest.main()