blob: cd33c90640ed048a817d553f1b21c8b226eaf875 (
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
|
"""
This contains a bunch of RFC7230 definitions and regular expressions that are
needed to properly parse HTTP messages.
"""
import re
from .compat import tobytes
WS = "[ \t]"
OWS = WS + "{0,}?"
RWS = WS + "{1,}?"
BWS = OWS
# RFC 7230 Section 3.2.6 "Field Value Components":
# tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*"
# / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
# / DIGIT / ALPHA
# obs-text = %x80-FF
TCHAR = r"[!#$%&'*+\-.^_`|~0-9A-Za-z]"
OBS_TEXT = r"\x80-\xff"
TOKEN = TCHAR + "{1,}"
# RFC 5234 Appendix B.1 "Core Rules":
# VCHAR = %x21-7E
# ; visible (printing) characters
VCHAR = r"\x21-\x7e"
# header-field = field-name ":" OWS field-value OWS
# field-name = token
# field-value = *( field-content / obs-fold )
# field-content = field-vchar [ 1*( SP / HTAB ) field-vchar ]
# field-vchar = VCHAR / obs-text
# Errata from: https://www.rfc-editor.org/errata_search.php?rfc=7230&eid=4189
# changes field-content to:
#
# field-content = field-vchar [ 1*( SP / HTAB / field-vchar )
# field-vchar ]
FIELD_VCHAR = "[" + VCHAR + OBS_TEXT + "]"
# Field content is more greedy than the ABNF, in that it will match the whole value
FIELD_CONTENT = FIELD_VCHAR + "+(?:[ \t]+" + FIELD_VCHAR + "+)*"
# Which allows the field value here to just see if there is even a value in the first place
FIELD_VALUE = "(?:" + FIELD_CONTENT + ")?"
HEADER_FIELD = re.compile(
tobytes(
"^(?P<name>" + TOKEN + "):" + OWS + "(?P<value>" + FIELD_VALUE + ")" + OWS + "$"
)
)
|
