aboutsummaryrefslogtreecommitdiffstats
path: root/tools/check_spelling.py
blob: 493e0ae49ecc0a2b519d4b5b37678dc706cc0fd8 (plain)
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
#!/usr/bin/env python3
# Wireshark - Network traffic analyzer
# By Gerald Combs <gerald@wireshark.org>
# Copyright 1998 Gerald Combs
#
# SPDX-License-Identifier: GPL-2.0-or-later

import os
import re
import subprocess
import argparse
import signal
from collections import Counter

# Looks for spelling errors among strings found in source or documentation files.
# TODO: deal with contractions - pyspellcheck doesn't seem to handle apostrophies..

# For text colouring/highlighting.
class bcolors:
    HEADER = '\033[95m'
    OKBLUE = '\033[94m'
    OKGREEN = '\033[92m'
    ADDED = '\033[45m'
    WARNING = '\033[93m'
    FAIL = '\033[91m'
    ENDC = '\033[0m'
    BOLD = '\033[1m'
    UNDERLINE = '\033[4m'


# Try to exit soon after Ctrl-C is pressed.
should_exit = False

def signal_handler(sig, frame):
    global should_exit
    should_exit = True
    print('You pressed Ctrl+C - exiting')

signal.signal(signal.SIGINT, signal_handler)



# Create spellchecker, and augment with some Wireshark words.
from spellchecker import SpellChecker
# Set up our dict with words from text file.
spell = SpellChecker()
spell.word_frequency.load_text_file('./tools/wireshark_words.txt')


# Track words that were not found.
missing_words = []


# Split camelCase string into separate words.
def camelCaseSplit(identifier):
    matches = re.finditer('.+?(?:(?<=[a-z])(?=[A-Z])|(?<=[A-Z])(?=[A-Z][a-z])|$)', identifier)
    return [m.group(0) for m in matches]


# A File object contains all of the strings to be checked for a given file.
class File:
    def __init__(self, file):
        self.file = file
        self.values = []

        filename, extension = os.path.splitext(file)
        self.code_file = extension in {'.c', '.cpp'}


        with open(file, 'r') as f:
            contents = f.read()

            if self.code_file:
                # Remove comments so as not to trip up RE.
                contents = removeComments(contents)

            # Find protocol name and add to dict.
            # N.B. doesn't work when a variable is used instead of a literal for the protocol name...
            matches =   re.finditer(r'proto_register_protocol\s*\([\n\r\s]*\"(.*)\",[\n\r\s]*\"(.*)\",[\n\r\s]*\"(.*)\"', contents)
            for m in matches:
                protocol = m.group(3)
                # Add to dict.
                spell.word_frequency.load_words([protocol])
                spell.known([protocol])
                print('Protocol is: ' + bcolors.BOLD +  protocol + bcolors.ENDC)

    # Add a string found in this file.
    def add(self, value):
        self.values.append(value)

    # Whole word is not recognised, but is it 2 words concatenated (without camelcase) ?
    def checkMultiWords(self, word):
        if len(word) < 6:
            return False

        # Don't consider if mixed cases.
        if not (word.islower() or word.isupper()):
            # But make an exception if only the fist letter is uppercase..
            if not word == (word[0].upper() + word[1:]):
                return False

        # Try splitting into 2 words recognised at various points.
        length = len(word)
        for idx in range(3, length-3):
            word1 = word[0:idx]
            word2 = word[idx:]

            if not spell.unknown([word1, word2]):
                return True

        return False


    # Check the spelling of all the words we have found fir tgus fuke,
    def spellCheck(self):

        num_values = len(self.values)
        this_value = 0
        for v in self.values:
            if should_exit:
                exit(1)

            this_value += 1

            # Ignore includes.
            if v.endswith('.h'):
                continue

            # Store original (as want to include for context in error report).
            original = str(v)

            # Replace most punctuation with spaces, and eliminate common format specifiers.
            v = v.replace('.', ' ')
            v = v.replace(',', ' ')
            v = v.replace('`', ' ')
            v = v.replace(':', ' ')
            v = v.replace(';', ' ')
            v = v.replace('"', ' ')
            v = v.replace('\\', ' ')
            v = v.replace('+', ' ')
            v = v.replace('|', ' ')
            v = v.replace('(', ' ')
            v = v.replace(')', ' ')
            v = v.replace('[', ' ')
            v = v.replace(']', ' ')
            v = v.replace('{', ' ')
            v = v.replace('}', ' ')
            v = v.replace('<', ' ')
            v = v.replace('>', ' ')
            v = v.replace('_', ' ')
            v = v.replace('-', ' ')
            v = v.replace('/', ' ')
            v = v.replace('!', ' ')
            v = v.replace('?', ' ')
            v = v.replace('=', ' ')
            v = v.replace('*', ' ')
            v = v.replace('%', ' ')
            v = v.replace('#', ' ')
            v = v.replace('&', ' ')
            v = v.replace('@', ' ')
            v = v.replace("'", ' ')
            v = v.replace('"', ' ')
            v = v.replace('%u', '')
            v = v.replace('%d', '')
            v = v.replace('%s', '')

            # Split into words.
            value_words = v.split()
            # Further split up any camelCase words.
            words = []
            for w in value_words:
                words +=  camelCaseSplit(w)

            # Check each word within this string in turn.
            for word in words:
                # Strip trailing digits from word.
                word = word.rstrip('1234567890')

                # Quote marks found in some of the docs...
                word = word.replace('“', '')
                word = word.replace('”', '')

                if len(word) > 4 and spell.unknown([word]) and not self.checkMultiWords(word):
                    print(self.file, this_value, '/', num_values, '"' + original + '"', bcolors.FAIL + word + bcolors.ENDC,
                         ' -> ', '?')
                    # TODO: this can be interesting, but takes too long!
                    # bcolors.OKGREEN + spell.correction(word) + bcolors.ENDC
                    global missing_words
                    missing_words.append(word)

def removeComments(code_string):
    code_string = re.sub(re.compile("/\*.*?\*/",re.DOTALL ) ,"" ,code_string) # C-style comment
    # Remove this for now as can get tripped up if see htpps://www.... within a string!
    #code_string = re.sub(re.compile("//.*?\n" ) ,"" ,code_string)             # C++-style comment
    return code_string

def removeSingleQuotes(code_string):
    code_string = code_string.replace('\"\\\\\"', "")
    code_string = code_string.replace("\\\"", " ")
    code_string = code_string.replace("'\"'", "")
    return code_string

def removeHexSpecifiers(code_string):
    # TODO: replace with single regexp?
    code_string = code_string.replace('0x%02X', "")
    code_string = code_string.replace('0x%02x', "")
    code_string = code_string.replace('0x%04X', "")
    code_string = code_string.replace('0x%04x', "")
    code_string = code_string.replace('0x%08X', "")
    code_string = code_string.replace('0x%08x', "")
    return code_string


# Create a File object that knows about all of the strings in the given file.
def findStrings(filename):
    with open(filename, 'r') as f:
        contents = f.read()

        # Remove comments & embedded quotes so as not to trip up RE.
        contents = removeComments(contents)
        contents = removeSingleQuotes(contents)
        contents = removeHexSpecifiers(contents)

        # Create file object.
        file = File(filename)

        # What we check depends upon file type.
        if file.code_file:
            # Code so only checking strings.
            matches =   re.finditer(r'\"([^\"]*)\"', contents)
            for m in matches:
                file.add(m.group(1))
        else:
            # A documentation file, so examine all words.
            words = contents.split()
            for w in words:
                file.add(w)

        return file


# Test for whether the given file was automatically generated.
def isGeneratedFile(filename):
    # Open file
    f_read = open(os.path.join(filename), 'r')
    lines_tested = 0
    for line in f_read:
        # The comment to say that its generated is near the top, so give up once
        # get a few lines down.
        if lines_tested > 10:
            f_read.close()
            return False
        if (line.find('Generated automatically') != -1 or
            line.find('Autogenerated from') != -1 or
            line.find('is autogenerated') != -1 or
            line.find('automatically generated by Pidl') != -1 or
            line.find('Created by: The Qt Meta Object Compiler') != -1):

            f_read.close()
            return True
        lines_tested = lines_tested + 1

    # OK, looks like a hand-written file!
    f_read.close()
    return False


def isAppropriateFile(filename):
    file, extension = os.path.splitext(filename)
    return extension in { '.adoc', '.c', '.cpp', '.pod'} or file.endswith('README')


def findFilesInFolder(folder):
    files_to_check = []

    for root, subfolders, files in os.walk(folder):
        for f in files:
            if should_exit:
                return

            f = os.path.join(root, f)
            if isAppropriateFile(f) and not isGeneratedFile(f):
                files_to_check.append(f)

    return files_to_check


# Check the given dissector file.
def checkFile(filename):
    file = findStrings(filename)
    file.spellCheck()



#################################################################
# Main logic.

# command-line args.  Controls which files should be checked.
# If no args given, will just scan epan/dissectors folder.
parser = argparse.ArgumentParser(description='Check calls in dissectors')
parser.add_argument('--file', action='store', default='',
                    help='specify individual dissector file to test')
parser.add_argument('--folder', action='store', default='',
                    help='specify folder to test')
parser.add_argument('--commits', action='store',
                    help='last N commits to check')
parser.add_argument('--open', action='store_true',
                    help='check open files')

args = parser.parse_args()


# Get files from wherever command-line args indicate.
files = []
if args.file:
    # Add single specified file..
    if not os.path.isfile(args.file):
        print('Chosen file', args.file, 'does not exist.')
        exit(1)
    else:
        files.append(args.file)
elif args.commits:
    # Get files affected by specified number of commits.
    command = ['git', 'diff', '--name-only', 'HEAD~' + args.commits]
    files = [f.decode('utf-8')
             for f in subprocess.check_output(command).splitlines()]
    # Will examine dissector files only
    files = list(filter(lambda f : isAppropriateFile(f), files))
elif args.open:
    # Unstaged changes.
    command = ['git', 'diff', '--name-only']
    files = [f.decode('utf-8')
             for f in subprocess.check_output(command).splitlines()]
    # Only interested in dissector files.
    files = list(filter(lambda f : isDissectorFile(f), files))
    # Staged changes.
    command = ['git', 'diff', '--staged', '--name-only']
    files_staged = [f.decode('utf-8')
                    for f in subprocess.check_output(command).splitlines()]
    # Only interested in dissector files.
    files_staged = list(filter(lambda f : isDissectorFile(f), files_staged))
    for f in files:
        files.append(f)
    for f in files_staged:
        if not f in files:
            files.append(f)
else:
    # By default, scan dissectors
    folder = os.path.join('epan', 'dissectors')
    # But overwrite with any folder entry.
    if args.folder:
        folder = args.folder
        if not os.path.isdir(folder):
            print('Folder', folder, 'not found!')
            exit(1)

    # Find files from folder.
    print('Looking for files in', folder)
    files = findFilesInFolder(folder)


# If scanning a subset of files, list them here.
print('Examining:')
if args.file or args.commits or args.open:
    if files:
        print(' '.join(files), '\n')
    else:
        print('No files to check.\n')
else:
    print('All dissector modules\n')


# Now check the chosen files.
for f in files:
    # Jump out if control-C has been pressed.
    if should_exit:
        exit(1)
    checkFile(f)



# Show the most commonly not-recognised words. TODO: depend upon a command-line option here?
print('')
counter = Counter(missing_words).most_common(100)
if len(counter) > 0:
    for c in counter:
        print(c[0], ':', c[1])

# Show error count.
print('\n' + bcolors.BOLD + str(len(missing_words)) + ' issues found' + bcolors.ENDC + '\n')