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
|
# -*- coding: utf-8 -*-
"""
pygments.lexers.mime
~~~~~~~~~~~~~~~~~~~~
Lexer for Multipurpose Internet Mail Extensions (MIME) data.
:copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import RegexLexer, include
from pygments.lexers import get_lexer_for_mimetype
from pygments.token import Text, Name, String, Operator, Comment, Other
from pygments.util import get_int_opt, ClassNotFound
__all__ = ["MIMELexer"]
class MIMELexer(RegexLexer):
"""
Lexer for Multipurpose Internet Mail Extensions (MIME) data. This lexer is
designed to process the nested mulitpart data.
It assumes that the given data contains both header and body (and is
splitted by empty line). If no valid header is found, then the entire data
would be treated as body.
Additional options accepted:
`MIME-max-level`
Max recurssion level for nested MIME structure. Any negative number
would treated as unlimited. (default: -1)
`Content-Type`
Treat the data as specific content type. Useful when header is
missing, or this lexer would try to parse from header. (default:
`text/plain`)
`Multipart-Boundary`
Set the default multipart boundary delimiter. This option is only used
when `Content-Type` is `multipart` and header is missing. This lexer
would try to parse from header by default. (default: None)
`Content-Transfer-Encoding`
Treat the data as specific encoding. Or this lexer would try to parse
from header by default. (default: None)
.. versionadded:: 2.5
"""
name = "MIME"
aliases = ["mime"]
mimetypes = ["multipart/mixed",
"multipart/related",
"multipart/alternative"]
def __init__(self, **options):
super(MIMELexer, self).__init__(**options)
self.boundary = options.get("Multipart-Boundary")
self.content_transfer_encoding = options.get("Content_Transfer_Encoding")
self.content_type = options.get("Content_Type", "text/plain")
self.max_nested_level = get_int_opt(options, "MIME-max-level", -1)
def analyse_text(text):
try:
header, body = text.strip().split("\n\n", 1)
if not body.strip():
return 0.1
invalid_headers = MIMELexer.tokens["header"].sub("", header)
if invalid_headers.strip():
return 0.1
else:
return 1
except ValueError:
return 0.1
def get_header_tokens(self, match):
field = match.group(1)
if field.lower() in self.attention_headers:
yield match.start(1), Name.Tag, field + ":"
yield match.start(2), Text.Whitespace, match.group(2)
pos = match.end(2)
body = match.group(3)
for i, t, v in self.get_tokens_unprocessed(body, ("root", field.lower())):
yield pos + i, t, v
else:
yield match.start(), Comment, match.group()
def get_body_tokens(self, match):
pos_body_start = match.start()
entire_body = match.group()
# skip first newline
if entire_body[0] == '\n':
yield pos_body_start, Text.Whitespace, u'\n'
pos_body_start = pos_body_start + 1
entire_body = entire_body[1:]
# if it is not a mulitpart
if not self.content_type.startswith("multipart") or not self.boundary:
for i, t, v in self.get_bodypart_tokens(entire_body):
yield pos_body_start + i, t, v
return
# find boundary
bdry_pattern = r"^--%s(--)?\n" % re.escape(self.boundary)
bdry_matcher = re.compile(bdry_pattern, re.MULTILINE)
# some data has prefix text before first boundary
m = bdry_matcher.search(entire_body)
if m:
pos_part_start = pos_body_start + m.end()
pos_iter_start = lpos_end = m.end()
yield pos_body_start, Text, entire_body[:m.start()]
yield pos_body_start + lpos_end, String.Delimiter, m.group()
else:
pos_part_start = pos_body_start
pos_iter_start = 0
# process tokens of each body part
for m in bdry_matcher.finditer(entire_body, pos_iter_start):
# bodypart
lpos_start = pos_part_start - pos_body_start
lpos_end = m.start()
part = entire_body[lpos_start:lpos_end]
for i, t, v in self.get_bodypart_tokens(part):
yield pos_part_start + i, t, v
# boundary
yield pos_body_start + lpos_end, String.Delimiter, m.group()
pos_part_start = pos_body_start + m.end()
# some data has suffix text after last boundary
lpos_start = pos_part_start - pos_body_start
if lpos_start != len(entire_body):
yield pos_part_start, Text, entire_body[lpos_start:]
def get_bodypart_tokens(self, text):
# return if:
# * no content
# * no content type specific
# * content encoding is not readable
# * max recurrsion exceed
if not text.strip() or not self.content_type:
return [(0, Other, text)]
cte = self.content_transfer_encoding
if cte and cte not in {"8bit", "7bit", "quoted-printable"}:
return [(0, Other, text)]
if self.max_nested_level == 0:
return [(0, Other, text)]
# get lexer
try:
lexer = get_lexer_for_mimetype(self.content_type)
except ClassNotFound:
return [(0, Other, text)]
if isinstance(lexer, type(self)):
lexer.max_nested_level = self.max_nested_level - 1
return lexer.get_tokens_unprocessed(text)
def store_content_type(self, match):
self.content_type = match.group(1)
prefix_len = match.start(1) - match.start(0)
yield match.start(0), Text.Whitespace, match.group(0)[:prefix_len]
yield match.start(1), Name.Label, match.group(2)
yield match.end(2), String.Delimiter, u"/"
yield match.start(3), Name.Label, match.group(3)
def get_content_type_subtokens(self, match):
yield match.start(1), Text, match.group(1)
yield match.start(2), Text.Whitespace, match.group(2)
yield match.start(3), Name.Attribute, match.group(3)
yield match.start(4), Operator, match.group(4)
yield match.start(5), String, match.group(5)
if match.group(3).lower() == "boundary":
boundary = match.group(5).strip()
if boundary[0] == '"' and boundary[-1] == '"':
boundary = boundary[1:-1]
self.boundary = boundary
def store_content_transfer_encoding(self, match):
self.content_transfer_encoding = match.group(0).lower()
yield match.start(0), Name.Constant, match.group(0)
attention_headers = {"content-type", "content-transfer-encoding"}
tokens = {
"root": [
(r"^([\w-]+):( *)([\s\S]*?\n)(?![ \t])", get_header_tokens),
(r"^$[\s\S]+", get_body_tokens),
],
"header": [
# folding
(r"\n[ \t]", Text.Whitespace),
(r"\n(?![ \t])", Text.Whitespace, "#pop"),
],
"content-type": [
include("header"),
(
r"^\s*((multipart|application|audio|font|image|model|text|video"
r"|message)/([\w-]+))",
store_content_type,
),
(r'(;)((?:[ \t]|\n[ \t])*)([\w:-]+)(=)([\s\S]*?)(?=;|\n(?![ \t]))',
get_content_type_subtokens),
(r';[ \t]*\n(?![ \t])', Text, '#pop'),
],
"content-transfer-encoding": [
include("header"),
(r"([\w-]+)", store_content_transfer_encoding),
],
}
|
