annotate MoinMoin/action/SpellCheck.py @ 5910:7e7e1cbb9d3f

security: fix remote code execution vulnerability in twikidraw/anywikidraw actions We have wikiutil.taintfilename() to make user supplied filenames safe, so that they can't contain any "special" characters like path separators, etc. It is used at many places in moin, but wasn't used here. :|
author Thomas Waldmann <tw AT waldmann-edv DOT de>
date Sat, 29 Dec 2012 15:05:29 +0100
parents dc3c0b894178
children
rev   line source
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
1 # -*- coding: iso-8859-1 -*-
2286
01f05e74aa9c Big PEP8 and whitespace cleanup
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1920
diff changeset
2 """
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
3 MoinMoin - Spelling Action
2286
01f05e74aa9c Big PEP8 and whitespace cleanup
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1920
diff changeset
4
01f05e74aa9c Big PEP8 and whitespace cleanup
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1920
diff changeset
5 Word adding based on code by Christian Bird <chris.bird@lineo.com>
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
6
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
7 This action checks for spelling errors in a page using one or several
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
8 word lists.
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
9
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
10 MoinMoin looks for dictionary files in the directory "dict" within the
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
11 MoinMoin package directory. To load the default UNIX word files, you
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
12 have to manually create symbolic links to those files (usually
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
13 '/usr/dict/words' or '/usr/share/dict/words').
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
14
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
15 Additionally, all words on the page "LocalSpellingWords" are added to
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
16 the list of valid words, if that page exists.
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
17
1918
bb2e053067fb fixing copyright headers: remove umlauts (encoding troubles), make epydoc compatible, reformat
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1900
diff changeset
18 @copyright: 2001 Richard Jones <richard@bizarsoftware.com.au>,
2286
01f05e74aa9c Big PEP8 and whitespace cleanup
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1920
diff changeset
19 2001-2004 Juergen Hermann <jh@web.de>
01f05e74aa9c Big PEP8 and whitespace cleanup
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1920
diff changeset
20 @license: GNU GPL, see COPYING for details.
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
21 """
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
22
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
23 import os, re, codecs
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
24 from MoinMoin import config, wikiutil
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
25 from MoinMoin.Page import Page
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
26
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
27
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
28 def _getWordsFiles(request):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
29 """Check a list of possible word files"""
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
30 candidates = []
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
31
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
32 # load a list of possible word files
123
0e91f640f242 local dict support, inspired by the Debian patch
Thomas Waldmann <tw@waldmann-edv.de>
parents: 0
diff changeset
33 for basedir in (request.cfg.moinmoin_dir, request.cfg.data_dir):
0e91f640f242 local dict support, inspired by the Debian patch
Thomas Waldmann <tw@waldmann-edv.de>
parents: 0
diff changeset
34 localdict = os.path.join(basedir, 'dict')
0e91f640f242 local dict support, inspired by the Debian patch
Thomas Waldmann <tw@waldmann-edv.de>
parents: 0
diff changeset
35 if os.path.isdir(localdict):
1866
0194beaf511e reduce reduce, filter and map usage
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1777
diff changeset
36 candidates.extend(
0194beaf511e reduce reduce, filter and map usage
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1777
diff changeset
37 [os.path.join(localdict, fn) for fn in os.listdir(localdict)])
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
38
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
39 # validate candidate list (leave out directories!)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
40 wordsfiles = []
1920
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
41 for f in candidates:
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
42 if os.path.isfile(f) and os.access(f, os.F_OK | os.R_OK):
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
43 wordsfiles.append(f)
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
44
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
45 # return validated file list
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
46 return wordsfiles
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
47
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
48 def _loadWords(lines, dict):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
49 for line in lines:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
50 words = line.split()
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
51 for word in words:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
52 dict[word.encode(config.charset)] = ''
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
53
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
54 def _loadWordsFile(request, dict, filename):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
55 request.clock.start('spellread')
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
56 try:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
57 try:
5865
dc3c0b894178 fix dictionary file reading crash under windows
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 4235
diff changeset
58 f = codecs.open(filename, 'r', config.charset)
1920
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
59 lines = f.readlines()
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
60 except UnicodeError:
5865
dc3c0b894178 fix dictionary file reading crash under windows
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 4235
diff changeset
61 f = codecs.open(filename, 'r', 'iso-8859-1')
1920
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
62 lines = f.readlines()
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
63 finally:
1920
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
64 f.close()
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
65 _loadWords(lines, dict)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
66 request.clock.stop('spellread')
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
67
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
68 def _loadWordsPage(request, dict, page):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
69 lines = page.getlines()
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
70 _loadWords(lines, dict)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
71
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
72
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
73 def _loadDict(request):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
74 """ Load words from words files or cached dict """
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
75 # check for "dbhash" module
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
76 try:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
77 import dbhash
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
78 except ImportError:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
79 dbhash = None
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
80
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
81 # load the words
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
82 cachename = os.path.join(request.cfg.data_dir, 'cache', 'spellchecker.dict')
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
83 if dbhash and os.path.exists(cachename):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
84 wordsdict = dbhash.open(cachename, "r")
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
85 else:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
86 wordsfiles = _getWordsFiles(request)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
87 if dbhash:
1427
5e4d0d49dd60 don't use mask, as we have os.umask() now
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1181
diff changeset
88 wordsdict = dbhash.open(cachename, 'n')
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
89 else:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
90 wordsdict = {}
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
91
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
92 for wordsfile in wordsfiles:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
93 _loadWordsFile(request, wordsdict, wordsfile)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
94
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
95 if dbhash:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
96 wordsdict.sync()
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
97
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
98 return wordsdict
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
99
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
100
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
101 def _addLocalWords(request):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
102 from MoinMoin.PageEditor import PageEditor
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
103 # get the new words as a string (if any are marked at all)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
104 try:
4201
40acd13fb3d6 Changed form access to MultiDict forms
Florian Krupicka <florian.krupicka@googlemail.com>
parents: 4168
diff changeset
105 newwords = request.form.getlist('newwords')
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
106 except KeyError:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
107 # no new words checked
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
108 return
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
109 newwords = u' '.join(newwords)
949
cbbde07e00c4 whitespace-only cleanup, small style changes
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 123
diff changeset
110
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
111 # get the page contents
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
112 lsw_page = PageEditor(request, request.cfg.page_local_spelling_words)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
113 words = lsw_page.get_raw_body()
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
114
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
115 # add the words to the page and save it
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
116 if words and words[-1] != '\n':
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
117 words = words + '\n'
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
118 lsw_page.saveText(words + '\n' + newwords, 0)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
119
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
120
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
121 def checkSpelling(page, request, own_form=1):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
122 """ Do spell checking, return a tuple with the result.
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
123 """
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
124 _ = request.getText
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
125
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
126 # first check to see if we we're called with a "newwords" parameter
1868
64507f46beb2 reduce usage of has_key()
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1866
diff changeset
127 if 'button_newwords' in request.form:
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
128 _addLocalWords(request)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
129
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
130 # load words
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
131 wordsdict = _loadDict(request)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
132
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
133 localwords = {}
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
134 lsw_page = Page(request, request.cfg.page_local_spelling_words)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
135 if lsw_page.exists():
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
136 _loadWordsPage(request, localwords, lsw_page)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
137
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
138 # init status vars & load page
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
139 request.clock.start('spellcheck')
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
140 badwords = {}
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
141 text = page.get_raw_body()
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
142
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
143 # checker regex and matching substitute function
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
144 word_re = re.compile(r'([%s]?[%s]+)' % (
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
145 config.chars_upper, config.chars_lower), re.UNICODE)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
146
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
147 def checkword(match, wordsdict=wordsdict, badwords=badwords,
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
148 localwords=localwords, num_re=re.compile(r'^\d+$', re.UNICODE)):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
149 word = match.group(1)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
150 if len(word) == 1:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
151 return ""
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
152 w_enc = word.encode(config.charset)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
153 wl_enc = word.lower().encode(config.charset)
1868
64507f46beb2 reduce usage of has_key()
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1866
diff changeset
154 if not (w_enc in wordsdict or wl_enc in wordsdict or
64507f46beb2 reduce usage of has_key()
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1866
diff changeset
155 w_enc in localwords or wl_enc in localwords):
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
156 if not num_re.match(word):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
157 badwords[word] = 1
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
158 return ""
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
159
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
160 # do the checking
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
161 for line in text.split('\n'):
1920
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
162 if line == '' or line[0] == '#':
b06ef2a53efa 'make pylint', fixed lots of minor stuff found by pylint (and there is still lots left to do)
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1918
diff changeset
163 continue
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
164 word_re.sub(checkword, line)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
165
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
166 if badwords:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
167 badwords = badwords.keys()
949
cbbde07e00c4 whitespace-only cleanup, small style changes
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 123
diff changeset
168 badwords.sort(lambda x, y: cmp(x.lower(), y.lower()))
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
169
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
170 # build regex recognizing the bad words
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
171 badwords_re = r'(^|(?<!\w))(%s)(?!\w)'
2286
01f05e74aa9c Big PEP8 and whitespace cleanup
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 1920
diff changeset
172 badwords_re = badwords_re % ("|".join([re.escape(bw) for bw in badwords]), )
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
173 badwords_re = re.compile(badwords_re, re.UNICODE)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
174
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
175 lsw_msg = ''
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
176 if localwords:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
177 lsw_msg = ' ' + _('(including %(localwords)d %(pagelink)s)') % {
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
178 'localwords': len(localwords), 'pagelink': lsw_page.link_to(request)}
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
179 msg = _('The following %(badwords)d words could not be found in the dictionary of '
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
180 '%(totalwords)d words%(localwords)s and are highlighted below:') % {
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
181 'badwords': len(badwords),
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
182 'totalwords': len(wordsdict)+len(localwords),
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
183 'localwords': lsw_msg} + "<br>"
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
184
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
185 # figure out what this action is called
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
186 action_name = os.path.splitext(os.path.basename(__file__))[0]
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
187
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
188 # add a form containing the bad words
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
189 if own_form:
4235
a6c315ff8d66 Make more use of werkzeugs Href object for URL-generation in MoinMoin
Florian Krupicka <florian.krupicka@googlemail.com>
parents: 4201
diff changeset
190 msg = msg + ('<form method="post" action="%s">\n'
a6c315ff8d66 Make more use of werkzeugs Href object for URL-generation in MoinMoin
Florian Krupicka <florian.krupicka@googlemail.com>
parents: 4201
diff changeset
191 '<input type="hidden" name="action" value="%s">\n') % (request.href(page.page_name), action_name)
949
cbbde07e00c4 whitespace-only cleanup, small style changes
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 123
diff changeset
192
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
193 checkbox = '<input type="checkbox" name="newwords" value="%(word)s">%(word)s&nbsp;&nbsp;'
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
194 msg = msg + (
3273
9c6900a92a64 more wikiutil.escape fixes
Thomas Waldmann <tw AT waldmann-edv DOT de>
parents: 3040
diff changeset
195 " ".join([checkbox % {'word': wikiutil.escape(w, True), } for w in badwords]) +
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
196 '<p><input type="submit" name="button_newwords" value="%s"></p>' %
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
197 _('Add checked words to dictionary')
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
198 )
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
199 if own_form:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
200 msg = msg + '</form>'
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
201 else:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
202 badwords_re = None
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
203 msg = _("No spelling errors found!")
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
204
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
205 request.clock.stop('spellcheck')
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
206
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
207 return badwords, badwords_re, msg
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
208
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
209
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
210 def execute(pagename, request):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
211 _ = request.getText
1900
89fffad859b5 SpellCheck: check if user may write to request.cfg.page_local_spelling_words
Reimar Bauer <rb.proj AT googlemail DOT com>
parents: 1868
diff changeset
212
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
213 page = Page(request, pagename)
1900
89fffad859b5 SpellCheck: check if user may write to request.cfg.page_local_spelling_words
Reimar Bauer <rb.proj AT googlemail DOT com>
parents: 1868
diff changeset
214 if not request.user.may.write(request.cfg.page_local_spelling_words):
2966
ba14d391c2ba Refactor all modules to use the new add_msg interface in 1.7 (done by Frederico Lorenzi). Should not be backported to 1.6 but
Alexander Schremmer <alex AT alexanderweb DOT de>
parents: 2286
diff changeset
215 request.theme.add_msg(_("You can't save spelling words."), "error")
ba14d391c2ba Refactor all modules to use the new add_msg interface in 1.7 (done by Frederico Lorenzi). Should not be backported to 1.6 but
Alexander Schremmer <alex AT alexanderweb DOT de>
parents: 2286
diff changeset
216 page.send_page()
1900
89fffad859b5 SpellCheck: check if user may write to request.cfg.page_local_spelling_words
Reimar Bauer <rb.proj AT googlemail DOT com>
parents: 1868
diff changeset
217 return
89fffad859b5 SpellCheck: check if user may write to request.cfg.page_local_spelling_words
Reimar Bauer <rb.proj AT googlemail DOT com>
parents: 1868
diff changeset
218
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
219 if request.user.may.read(pagename):
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
220 badwords, badwords_re, msg = checkSpelling(page, request)
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
221 else:
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
222 badwords = []
2966
ba14d391c2ba Refactor all modules to use the new add_msg interface in 1.7 (done by Frederico Lorenzi). Should not be backported to 1.6 but
Alexander Schremmer <alex AT alexanderweb DOT de>
parents: 2286
diff changeset
223 request.theme.add_msg(_("You can't check spelling on a page you can't read."), "error")
3034
d0d9fbc0f0ee PEP8 whitespace fixes
Reimar Bauer <rb.proj AT googlemail DOT com>
parents: 2966
diff changeset
224
2966
ba14d391c2ba Refactor all modules to use the new add_msg interface in 1.7 (done by Frederico Lorenzi). Should not be backported to 1.6 but
Alexander Schremmer <alex AT alexanderweb DOT de>
parents: 2286
diff changeset
225 request.theme.add_msg(msg, "dialog")
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
226 if badwords:
2966
ba14d391c2ba Refactor all modules to use the new add_msg interface in 1.7 (done by Frederico Lorenzi). Should not be backported to 1.6 but
Alexander Schremmer <alex AT alexanderweb DOT de>
parents: 2286
diff changeset
227 page.send_page(hilite_re=badwords_re)
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
228 else:
2966
ba14d391c2ba Refactor all modules to use the new add_msg interface in 1.7 (done by Frederico Lorenzi). Should not be backported to 1.6 but
Alexander Schremmer <alex AT alexanderweb DOT de>
parents: 2286
diff changeset
229 page.send_page()
0
77665d8e2254 tag of nonpublic@localhost--archive/moin--enterprise--1.5--base-0
Thomas Waldmann <tw-public@gmx.de>
parents:
diff changeset
230