Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(29)

Side by Side Diff: third_party/pylint/pylint/checkers/spelling.py

Issue 1920403002: [content/test/gpu] Run pylint check of gpu tests in unittest instead of PRESUBMIT (Closed) Base URL: https://chromium.googlesource.com/chromium/src.git@master
Patch Set: Update path to LICENSE.txt of logilab/README.chromium Created 4 years, 7 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch
OLDNEW
(Empty)
1 # Copyright 2014 Michal Nowikowski.
2 #
3 # This program is free software; you can redistribute it and/or modify it under
4 # the terms of the GNU General Public License as published by the Free Software
5 # Foundation; either version 2 of the License, or (at your option) any later
6 # version.
7 #
8 # This program is distributed in the hope that it will be useful, but WITHOUT
9 # ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
10 # FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
11 #
12 # You should have received a copy of the GNU General Public License along with
13 # this program; if not, write to the Free Software Foundation, Inc.,
14 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
15 """Checker for spelling errors in comments and docstrings.
16 """
17
18 import sys
19 import tokenize
20 import string
21 import re
22
23 if sys.version_info[0] >= 3:
24 maketrans = str.maketrans
25 else:
26 maketrans = string.maketrans
27
28 from pylint.interfaces import ITokenChecker, IAstroidChecker
29 from pylint.checkers import BaseTokenChecker
30 from pylint.checkers.utils import check_messages
31
32 try:
33 import enchant
34 except ImportError:
35 enchant = None
36
37 if enchant is not None:
38 br = enchant.Broker()
39 dicts = br.list_dicts()
40 dict_choices = [''] + [d[0] for d in dicts]
41 dicts = ["%s (%s)" % (d[0], d[1].name) for d in dicts]
42 dicts = ", ".join(dicts)
43 instr = ""
44 else:
45 dicts = "none"
46 dict_choices = ['']
47 instr = " To make it working install python-enchant package."
48
49 table = maketrans("", "")
50
51 class SpellingChecker(BaseTokenChecker):
52 """Check spelling in comments and docstrings"""
53 __implements__ = (ITokenChecker, IAstroidChecker)
54 name = 'spelling'
55 msgs = {
56 'C0401': ('Wrong spelling of a word \'%s\' in a comment:\n%s\n'
57 '%s\nDid you mean: \'%s\'?',
58 'wrong-spelling-in-comment',
59 'Used when a word in comment is not spelled correctly.'),
60 'C0402': ('Wrong spelling of a word \'%s\' in a docstring:\n%s\n'
61 '%s\nDid you mean: \'%s\'?',
62 'wrong-spelling-in-docstring',
63 'Used when a word in docstring is not spelled correctly.'),
64 }
65 options = (('spelling-dict',
66 {'default' : '', 'type' : 'choice', 'metavar' : '<dict name>',
67 'choices': dict_choices,
68 'help' : 'Spelling dictionary name. '
69 'Available dictionaries: %s.%s' % (dicts, instr)}),
70 ('spelling-ignore-words',
71 {'default' : '',
72 'type' : 'string',
73 'metavar' : '<comma separated words>',
74 'help' : 'List of comma separated words that '
75 'should not be checked.'}),
76 ('spelling-private-dict-file',
77 {'default' : '',
78 'type' : 'string',
79 'metavar' : '<path to file>',
80 'help' : 'A path to a file that contains private '
81 'dictionary; one word per line.'}),
82 ('spelling-store-unknown-words',
83 {'default' : 'n', 'type' : 'yn', 'metavar' : '<y_or_n>',
84 'help' : 'Tells whether to store unknown words to '
85 'indicated private dictionary in '
86 '--spelling-private-dict-file option instead of '
87 'raising a message.'}),
88 )
89
90 def open(self):
91 self.initialized = False
92 self.private_dict_file = None
93
94 if enchant is None:
95 return
96 dict_name = self.config.spelling_dict
97 if not dict_name:
98 return
99
100 self.ignore_list = [w.strip() for w in self.config.spelling_ignore_words .split(",")]
101 # "param" appears in docstring in param description and
102 # "pylint" appears in comments in pylint pragmas.
103 self.ignore_list.extend(["param", "pylint"])
104
105 if self.config.spelling_private_dict_file:
106 self.spelling_dict = enchant.DictWithPWL(
107 dict_name, self.config.spelling_private_dict_file)
108 self.private_dict_file = open(
109 self.config.spelling_private_dict_file, "a")
110 else:
111 self.spelling_dict = enchant.Dict(dict_name)
112
113 if self.config.spelling_store_unknown_words:
114 self.unknown_words = set()
115
116 # Prepare regex for stripping punctuation signs from text.
117 # ' and _ are treated in a special way.
118 puncts = string.punctuation.replace("'", "").replace("_", "")
119 self.punctuation_regex = re.compile('[%s]' % re.escape(puncts))
120 self.initialized = True
121
122 def close(self):
123 if self.private_dict_file:
124 self.private_dict_file.close()
125
126 def _check_spelling(self, msgid, line, line_num):
127 line2 = line.strip()
128 # Replace ['afadf with afadf (but preserve don't)
129 line2 = re.sub("'([^a-zA-Z]|$)", " ", line2)
130 # Replace afadf'] with afadf (but preserve don't)
131 line2 = re.sub("([^a-zA-Z]|^)'", " ", line2)
132 # Replace punctuation signs with space e.g. and/or -> and or
133 line2 = self.punctuation_regex.sub(' ', line2)
134
135 words = []
136 for word in line2.split():
137 # Skip words with digits.
138 if len(re.findall(r"\d", word)) > 0:
139 continue
140
141 # Skip words with mixed big and small letters,
142 # they are probaly class names.
143 if (len(re.findall("[A-Z]", word)) > 0 and
144 len(re.findall("[a-z]", word)) > 0 and
145 len(word) > 2):
146 continue
147
148 # Skip words with _ - they are probably function parameter names.
149 if word.count('_') > 0:
150 continue
151
152 words.append(word)
153
154 # Go through words and check them.
155 for word in words:
156 # Skip words from ignore list.
157 if word in self.ignore_list:
158 continue
159
160 orig_word = word
161 word = word.lower()
162
163 # Strip starting u' from unicode literals and r' from raw strings.
164 if (word.startswith("u'") or
165 word.startswith('u"') or
166 word.startswith("r'") or
167 word.startswith('r"')) and len(word) > 2:
168 word = word[2:]
169
170 # If it is a known word, then continue.
171 if self.spelling_dict.check(word):
172 continue
173
174 # Store word to private dict or raise a message.
175 if self.config.spelling_store_unknown_words:
176 if word not in self.unknown_words:
177 self.private_dict_file.write("%s\n" % word)
178 self.unknown_words.add(word)
179 else:
180 # Present up to 4 suggestions.
181 # TODO: add support for customising this.
182 suggestions = self.spelling_dict.suggest(word)[:4]
183
184 m = re.search(r"(\W|^)(%s)(\W|$)" % word, line.lower())
185 if m:
186 # Start position of second group in regex.
187 col = m.regs[2][0]
188 else:
189 col = line.lower().index(word)
190 indicator = (" " * col) + ("^" * len(word))
191
192 self.add_message(msgid, line=line_num,
193 args=(orig_word, line,
194 indicator,
195 "' or '".join(suggestions)))
196
197 def process_tokens(self, tokens):
198 if not self.initialized:
199 return
200
201 # Process tokens and look for comments.
202 for (tok_type, token, (start_row, _), _, _) in tokens:
203 if tok_type == tokenize.COMMENT:
204 self._check_spelling('wrong-spelling-in-comment',
205 token, start_row)
206
207 @check_messages('wrong-spelling-in-docstring')
208 def visit_module(self, node):
209 if not self.initialized:
210 return
211 self._check_docstring(node)
212
213 @check_messages('wrong-spelling-in-docstring')
214 def visit_class(self, node):
215 if not self.initialized:
216 return
217 self._check_docstring(node)
218
219 @check_messages('wrong-spelling-in-docstring')
220 def visit_function(self, node):
221 if not self.initialized:
222 return
223 self._check_docstring(node)
224
225 def _check_docstring(self, node):
226 """check the node has any spelling errors"""
227 docstring = node.doc
228 if not docstring:
229 return
230
231 start_line = node.lineno + 1
232
233 # Go through lines of docstring
234 for idx, line in enumerate(docstring.splitlines()):
235 self._check_spelling('wrong-spelling-in-docstring',
236 line, start_line + idx)
237
238
239 def register(linter):
240 """required method to auto register this checker """
241 linter.register_checker(SpellingChecker(linter))
OLDNEW
« no previous file with comments | « third_party/pylint/pylint/checkers/similar.py ('k') | third_party/pylint/pylint/checkers/stdlib.py » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698