/
linter.py
605 lines (481 loc) · 18.2 KB
/
linter.py
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
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
import re
import uuid
from collections import namedtuple
from itertools import zip_longest
from dennis.tools import (
VariableTokenizer,
all_subclasses,
parse_dennis_note,
parse_pofile,
)
IdString = namedtuple("IdString", ("msgid_fields", "msgid_strings"))
TranslatedString = namedtuple(
"TranslatedString",
("msgid_fields", "msgid_strings", "msgstr_field", "msgstr_string"),
)
WARNING = "warn"
ERROR = "err"
class HTMLParseError(Exception):
pass
class LintMessage:
def __init__(self, kind, line, col, code, msg, poentry):
self.kind = kind
self.line = line
self.col = col
self.code = code
self.msg = msg
self.poentry = poentry
def __repr__(self):
return "<LintedMessage {} {}:{} {} {}>".format(
self.kind, self.line, self.col, self.code, self.msg
)
class LintedEntry:
def __init__(self, poentry):
self.poentry = poentry
self.msgid = poentry.msgid
@property
def str(self):
poentry = self.poentry
if poentry.msgid_plural:
msgid_fields = ("msgid", "msgid_plural")
msgid_strings = (poentry.msgid, poentry.msgid_plural)
else:
msgid_fields = ("msgid",)
msgid_strings = (poentry.msgid,)
return IdString(msgid_fields, msgid_strings)
@property
def strs(self):
poentry = self.poentry
strs = []
if not poentry.msgid_plural:
strs.append(
TranslatedString(["msgid"], [poentry.msgid], "msgstr", poentry.msgstr)
)
else:
msgid_fields = ("msgid", "msgid_plural")
msgid_strings = (poentry.msgid, poentry.msgid_plural)
for key in sorted(poentry.msgstr_plural.keys()):
strs.append(
TranslatedString(
msgid_fields,
msgid_strings,
"msgstr[{}]".format(key),
poentry.msgstr_plural[key],
)
)
# List of TranslatedStrings
return strs
class LintRule:
num = ""
name = ""
desc = ""
def lint(self, vartok, linted_entry):
"""Takes a linted entry and generates LintMessages
:arg vartok: the variable tokenizer for extracting variables
:arg linted_entry: the LintedEntry to work on
:returns: list of LintMeessages or empty list
"""
raise NotImplementedError
class MalformedNoTypeLintRule(LintRule):
num = "E101"
name = "notype"
desc = "%(count) with no type at the end"
def lint(self, vartok, linted_entry):
msgs = []
# This only applies if one of the variable tokenizers is python-format.
if not vartok.contains("python-format"):
return msgs
malformed_re = re.compile(
r"(?:"
r"%" # %
r"[\(][^\)\s]+[\)]" # things in parens or not
r"(?:(?=[^diouxefGgcrs])|$)" # end of string or something that's not a format char
r")"
)
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
malformed = malformed_re.findall(trstr.msgstr_string)
if not malformed:
continue
malformed = [item.strip() for item in malformed]
msgs.append(
LintMessage(
ERROR,
linted_entry.poentry.linenum,
0,
self.num,
"type missing: {}".format(", ".join(malformed)),
linted_entry.poentry,
)
)
return msgs
class MalformedMissingRightBraceLintRule(LintRule):
num = "E102"
name = "missingrightbrace"
desc = "{foo with missing }"
def lint(self, vartok, linted_entry):
msgs = []
# This only applies if one of the variable tokenizers is python-brace-format.
if not vartok.contains("python-brace-format"):
return []
malformed_re = re.compile(r"(?:\{[^\}]+(?:\{|$))")
double_open = str(uuid.uuid4())
double_close = str(uuid.uuid4())
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
malformed = malformed_re.findall(
trstr.msgstr_string.replace("{{", double_open).replace(
"}}", double_close
)
)
if not malformed:
continue
malformed = [
item.strip().replace(double_open, "{{").replace(double_close, "}}")
for item in malformed
]
msgs.append(
LintMessage(
ERROR,
linted_entry.poentry.linenum,
0,
self.num,
"missing right curly-brace: {}".format(", ".join(malformed)),
linted_entry.poentry,
)
)
return msgs
class MalformedMissingLeftBraceLintRule(LintRule):
num = "E103"
name = "missingleftbrace"
desc = "foo} with missing {"
def lint(self, vartok, linted_entry):
msgs = []
# This only applies if one of the variable tokenizers is python-brace-format.
if not vartok.contains("python-brace-format"):
return []
malformed_re = re.compile(r"(?:(?:^|\})[^\{]*\})")
double_open = str(uuid.uuid4())
double_close = str(uuid.uuid4())
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
malformed = malformed_re.findall(
trstr.msgstr_string.replace("{{", double_open).replace(
"}}", double_close
)
)
if not malformed:
continue
malformed = [
item.strip().replace(double_open, "{{").replace(double_close, "}}")
for item in malformed
]
msgs.append(
LintMessage(
ERROR,
linted_entry.poentry.linenum,
0,
self.num,
"missing left curly-brace: {}".format(", ".join(malformed)),
linted_entry.poentry,
)
)
return msgs
class BadFormatLintRule(LintRule):
num = "E104"
name = "badformat"
desc = "% followed by a bad format character"
def lint(self, vartok, linted_entry):
msgs = []
# This only applies if one of the variable tokenizers is python-format.
if not vartok.contains("python-format"):
return []
splitter = re.compile(r"(\%(?:.|$))")
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
msgid_tokens = list(vartok.extract_tokens(" ".join(trstr.msgid_strings)))
if not msgid_tokens:
continue
# FIXME: Pretty sure we can just check the first token because they'll
# all have to be the same kind of thing.
first_token = msgid_tokens[0]
if not (len(first_token) == 2 and first_token[0] == "%"):
continue
for match in splitter.findall(trstr.msgstr_string):
if len(match) == 1 or match[1] not in "(diouxefGgcrs%":
msgs.append(
LintMessage(
ERROR,
linted_entry.poentry.linenum,
0,
self.num,
"bad format character: {}".format(match),
linted_entry.poentry,
)
)
return msgs
class MissingVarsLintRule(LintRule):
num = "W202"
num_error = "E202"
name = "missingvars"
desc = "Checks for variables in msgid, but missing in msgstr"
def lint(self, vartok, linted_entry):
msgs = []
# If there are no variable formats, skip this rule.
if not vartok.formats:
return []
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
if len(trstr.msgid_strings) > 1:
# If the msgstr uses a variable that isn't in any of
# the msgid strings, then that's an error (and handled
# by a different LintRule). Anything else we should
# ignore.
continue
msgid_tokens = vartok.extract_tokens(" ".join(trstr.msgid_strings))
msgstr_tokens = vartok.extract_tokens(trstr.msgstr_string)
missing = msgid_tokens.difference(msgstr_tokens)
if missing:
if vartok.contains("python-format") and len(
[var for var in missing if len(var) == 2 and var[0] == "%"]
):
# If we're looking at python-format variables and one of these is a
# python-format variable like %s, then this is an error--not a warning.
msgs.append(
LintMessage(
ERROR,
linted_entry.poentry.linenum,
0,
self.num_error,
"missing variables: {}".format(", ".join(sorted(missing))),
linted_entry.poentry,
)
)
else:
# If this is not python-format variables, then this is just a warning.
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num,
"missing variables: {}".format(", ".join(sorted(missing))),
linted_entry.poentry,
)
)
return msgs
class BlankLintRule(LintRule):
num = "W301"
name = "blank"
desc = "Translated string is only whitespace"
def lint(self, vartok, linted_entry):
msgs = []
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
if trstr.msgstr_string.isspace():
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num,
"translated string is solely whitespace",
linted_entry.poentry,
)
)
return msgs
class UnchangedLintRule(LintRule):
num = "W302"
name = "unchanged"
desc = "Makes sure string is actually translated"
def lint(self, vartok, linted_entry):
msgs = []
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
if trstr.msgstr_string in trstr.msgid_strings:
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num,
"translated string is same as source string",
linted_entry.poentry,
)
)
return msgs
class MismatchedHTMLLintRule(LintRule):
num = "W303"
num_error = "W304"
name = "html"
desc = "Checks for matching html between source and translated strings"
def lint(self, vartok, linted_entry):
msgs = []
from dennis.translator import HTMLExtractorTransform, Token
html = HTMLExtractorTransform()
def equiv(left, right):
return left == right
def tokenize(text):
"""Tokenizes the text using the HTMLExtractorTransform
:raises HTMLParseError: If it's invalid HTML.
"""
tokens = [
token
for token in html.transform(vartok, [Token(text)])
if token.type == "html" and not token.s.startswith("&")
]
return sorted(tokens, key=lambda token: token.s)
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
try:
msgid_parts = tokenize(trstr.msgid_strings[0])
except HTMLParseError as exc:
errmsg = "invalid html: msgid has invalid html {}".format(exc)
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num_error,
errmsg,
linted_entry.poentry,
)
)
return msgs
if len(trstr.msgid_strings) > 1:
# If this is a plural, then we check to see if the two
# msgid strings match each other. If not, then we move
# on because I have no idea what to do in this case.
try:
msgid_plural_parts = tokenize(trstr.msgid_strings[1])
except HTMLParseError as exc:
errmsg = "invalid html: msgid_plural has invalid html {}".format(
exc
)
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num_error,
errmsg,
linted_entry.poentry,
)
)
return msgs
zipped_parts = zip_longest(
msgid_parts, msgid_plural_parts, fillvalue=None
)
for left, right in zipped_parts:
if not left or not right or not equiv(left, right):
return []
try:
msgstr_parts = tokenize(trstr.msgstr_string)
except HTMLParseError as exc:
errmsg = "invalid html: msgstr has invalid html {}".format(exc)
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num_error,
errmsg,
linted_entry.poentry,
)
)
return msgs
for left, right in zip_longest(msgid_parts, msgstr_parts, fillvalue=None):
if not left or not right or not equiv(left, right):
msgs.append(
LintMessage(
WARNING,
linted_entry.poentry.linenum,
0,
self.num,
'different html: "{}" vs. "{}"'.format(
left.s if left else "", right.s if right else ""
),
linted_entry.poentry,
)
)
break
return msgs
class InvalidVarsLintRule(LintRule):
num = "E201"
name = "invalidvars"
desc = "Checks for variables not in msgid, but in msgstr"
def lint(self, vartok, linted_entry):
# If there are no variable formats, skip this rule.
if not vartok.formats:
return []
msgs = []
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
msgid_tokens = vartok.extract_tokens(" ".join(trstr.msgid_strings))
# If this is python-format or python-brace-format and there are
# no tokens in the msgid, then "no tokens, no problem".
if not msgid_tokens:
continue
msgstr_tokens = vartok.extract_tokens(trstr.msgstr_string)
invalid = msgstr_tokens.difference(msgid_tokens)
if invalid:
msgs.append(
LintMessage(
ERROR,
linted_entry.poentry.linenum,
0,
self.num,
"invalid variables: {}".format(", ".join(sorted(invalid))),
linted_entry.poentry,
)
)
return msgs
def get_lint_rules(with_names=False):
lint_rules = {}
for cls in all_subclasses(LintRule):
if cls.num:
lint_rules[cls.num] = cls
if with_names and cls.name:
lint_rules[cls.name] = cls
return lint_rules
def convert_rules(rules_spec):
lint_rules = get_lint_rules(with_names=True)
rules = [lint_rules[rule]() for rule in rules_spec if rule in lint_rules]
return rules
class Linter:
def __init__(self, vars_, rules_spec):
self.vartok = VariableTokenizer(vars_)
self.rules_spec = rules_spec
self.rules = convert_rules(self.rules_spec)
def lint_poentry(self, poentry):
linted_entry = LintedEntry(poentry)
skip = parse_dennis_note(poentry.comment)
msgs = []
# Check the comment to see if what we should ignore.
for lint_rule in self.rules:
if skip == "*" or lint_rule.num in skip:
continue
msgs.extend(lint_rule.lint(self.vartok, linted_entry))
return msgs
def verify_file(self, filename_or_string):
"""Verifies strings in file.
:arg filename_or_string: filename to verify or the contents of
a pofile as a string
:returns: list of LintMessage objects
:raises IOError: if the file is not a valid .po file or
doesn't exist
"""
po = parse_pofile(filename_or_string)
msgs = []
for entry in po.translated_entries():
msgs.extend(self.lint_poentry(entry))
return msgs