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
|
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
import re, rfc822
from lexer import Lexicon, LexError
from parser import Parser, ParseError
l = Lexicon()
LPAREN = l.define("LPAREN", r"\(")
RPAREN = l.define("LPAREN", r"\)")
SLASH = l.define("SLASH", r"/")
SEMI = l.define("SEMI", r";")
EQUAL = l.define("EQUAL", r"=")
TOKEN = l.define("TOKEN", r'[^()<>@,;:\\"/\[\]?= ]+')
STRING = l.define("STRING", r'"(?:[^\\"]|\\.)*"')
WSPACE = l.define("WSPACE", r"[ \n\r\t]+")
EOF = l.eof("EOF")
LEXER = l.compile()
def lex(st):
return LEXER.lex(st)
class MimeTypeParser(Parser):
def __init__(self, tokens):
Parser.__init__(self, [t for t in tokens if t.type is not WSPACE])
def parse(self):
result = self.mimetype()
self.eat(EOF)
return result
def mimetype(self):
self.remove_comments()
self.reset()
type = self.eat(TOKEN).value.lower()
self.eat(SLASH)
subtype = self.eat(TOKEN).value.lower()
params = []
while True:
if self.matches(SEMI):
params.append(self.parameter())
else:
break
return type, subtype, params
def remove_comments(self):
while True:
self.eat_until(LPAREN, EOF)
if self.matches(LPAREN):
self.remove(*self.comment())
else:
break
def comment(self):
start = self.eat(LPAREN)
while True:
self.eat_until(LPAREN, RPAREN)
if self.matches(LPAREN):
self.comment()
else:
break
end = self.eat(RPAREN)
return start, end
def parameter(self):
self.eat(SEMI)
name = self.eat(TOKEN).value
self.eat(EQUAL)
value = self.value()
return name, value
def value(self):
if self.matches(TOKEN):
return self.eat().value
elif self.matches(STRING):
return rfc822.unquote(self.eat().value)
else:
raise ParseError(self.next(), TOKEN, STRING)
def parse(addr):
return MimeTypeParser(lex(addr)).parse()
__all__ = ["parse", "ParseError"]
|