Mercurial > p > roundup > code
annotate roundup/cgi/accept_language.py @ 8019:16cc72cd9c17
fix: Send Vary: Accept-Encoding on any data that could be compressed
This allows upstream caches to return the correct data even when
compression is not in use. It is not sent if the content would never
be compressed. I.E. size < 100 bytes, dynamic compression
disabled, file would not benefit from compression (img/jpeg, img/png).
Fix setVary to add header to vary list only if it's not already there.
Found by redbot.org testing.
References:
https://www.stackpath.com/blog/accept-encoding-vary-important/
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Sun, 02 Jun 2024 18:22:53 -0400 |
| parents | 63c9680eed20 |
| children |
| rev | line source |
|---|---|
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
1 """Parse the Accept-Language header as defined in RFC2616. |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
2 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
3 See http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.4 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
4 for details. This module should follow the spec. |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
5 Author: Hernan M. Foffani (hfoffani@gmail.com) |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
6 Some use samples: |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
7 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
8 >>> parse("da, en-gb;q=0.8, en;q=0.7") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
9 ['da', 'en_gb', 'en'] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
10 >>> parse("en;q=0.2, fr;q=1") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
11 ['fr', 'en'] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
12 >>> parse("zn; q = 0.2 ,pt-br;q =1") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
13 ['pt_br', 'zn'] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
14 >>> parse("es-AR") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
15 ['es_AR'] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
16 >>> parse("es-es-cat") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
17 ['es_es_cat'] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
18 >>> parse("") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
19 [] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
20 >>> parse(None) |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
21 [] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
22 >>> parse(" ") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
23 [] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
24 >>> parse("en,") |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
25 ['en'] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
26 """ |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
27 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
28 import re |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
29 import heapq |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
30 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
31 # regexp for languange-range search |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
32 nqlre = "([A-Za-z]+[-[A-Za-z]+]*)$" |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
33 # regexp for languange-range search with quality value |
|
6030
ed8a9974c1bd
flake8 cleanups. whie space changes.
John Rouillard <rouilj@ieee.org>
parents:
5809
diff
changeset
|
34 qlre = r"([A-Za-z]+[-[A-Za-z]+]*);q=([\d\.]+)" |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
35 # both |
|
6030
ed8a9974c1bd
flake8 cleanups. whie space changes.
John Rouillard <rouilj@ieee.org>
parents:
5809
diff
changeset
|
36 lre = re.compile(nqlre + "|" + qlre) |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
37 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
38 whitespace = ' \t\n\r\v\f' |
|
5439
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
39 try: |
|
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
40 # Python 3. |
|
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
41 remove_ws = (str.maketrans('', '', whitespace),) |
|
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
42 except AttributeError: |
|
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
43 # Python 2. |
|
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
44 remove_ws = (None, whitespace) |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
45 |
|
6030
ed8a9974c1bd
flake8 cleanups. whie space changes.
John Rouillard <rouilj@ieee.org>
parents:
5809
diff
changeset
|
46 |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
47 def parse(language_header): |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
48 """parse(string_with_accept_header_content) -> languages list""" |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
49 |
|
6980
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
50 if language_header is None: return [] # noqa: E701 |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
51 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
52 # strip whitespaces. |
|
5439
b00cd44fea16
Python 3 preparation: update string translate method call in cgi/accept_language.py.
Joseph Myers <jsm@polyomino.org.uk>
parents:
4362
diff
changeset
|
53 lh = language_header.translate(*remove_ws) |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
54 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
55 # if nothing, return |
|
6980
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
56 if lh == "": return [] # noqa: E701 |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
57 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
58 # split by commas and parse the quality values. |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
59 pls = [lre.findall(x) for x in lh.split(',')] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
60 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
61 # drop uncomformant |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
62 qls = [x[0] for x in pls if len(x) > 0] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
63 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
64 # use a heap queue to sort by quality values. |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
65 # the value of each item is 1.0 complement. |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
66 pq = [] |
|
6980
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
67 order = 0 |
|
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
68 for lang in qls: |
|
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
69 order += 1 |
|
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
70 if lang[0] != '': |
|
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
71 heapq.heappush(pq, (0.0, order, lang[0])) |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
72 else: |
|
6980
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
73 heapq.heappush(pq, (1.0-float(lang[2]), order, lang[1])) |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
74 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
75 # get the languages ordered by quality |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
76 # and replace - by _ |
|
6980
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
77 return [heapq.heappop(pq)[2].replace('-', '_') for x in range(len(pq))] |
|
63c9680eed20
fake8 whitespace; variable name replacement
John Rouillard <rouilj@ieee.org>
parents:
6347
diff
changeset
|
78 |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
79 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
80 if __name__ == "__main__": |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
81 import doctest |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
82 doctest.testmod() |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
83 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
84 # vim: set et sts=4 sw=4 : |
