Mercurial > p > roundup > code
annotate roundup/cgi/accept_language.py @ 5108:67fad01d2009
issue2550653: xapian search, stemming is not working
This is a partial fix for the issue. It does make stemming work
(so searching for silent will also return docs with silently in
them). However to do this we need to lowercase the text so the
porter stemmer will work. This means capitalization is not
preserved.
Tests in test/test_indexer for xapian backend all pass.
David Wolever (wolever) did the work.
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Mon, 27 Jun 2016 22:10:45 -0400 |
| parents | 74476eaac38a |
| children | b00cd44fea16 |
| 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 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
34 qlre = "([A-Za-z]+[-[A-Za-z]+]*);q=([\d\.]+)" |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
35 # both |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
36 lre = re.compile(nqlre + "|" + qlre) |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
37 |
|
4362
74476eaac38a
more modernisation
Richard Jones <richard@users.sourceforge.net>
parents:
3426
diff
changeset
|
38 ascii = ''.join([chr(x) for x in range(256)]) |
|
3426
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
39 whitespace = ' \t\n\r\v\f' |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
40 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
41 def parse(language_header): |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
42 """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
|
43 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
44 if language_header is None: return [] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
45 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
46 # strip whitespaces. |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
47 lh = language_header.translate(ascii, whitespace) |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
48 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
49 # if nothing, return |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
50 if lh == "": return [] |
|
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 # 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
|
53 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
|
54 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
55 # drop uncomformant |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
56 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
|
57 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
58 # 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
|
59 # 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
|
60 pq = [] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
61 for l in qls: |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
62 if l[0] != '': |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
63 heapq.heappush(pq, (0.0, l[0])) |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
64 else: |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
65 heapq.heappush(pq, (1.0-float(l[2]), l[1])) |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
66 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
67 # 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
|
68 # and replace - by _ |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
69 return [x[1].replace('-','_') for x in pq] |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
70 |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
71 if __name__ == "__main__": |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
72 import doctest |
|
52f89836d05b
Parse the Accept-Language header as defined in RFC2616.
Alexander Smishlajev <a1s@users.sourceforge.net>
parents:
diff
changeset
|
73 doctest.testmod() |
|
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 # vim: set et sts=4 sw=4 : |
