File: check-code.py

package info (click to toggle)
mercurial 1.6.4-1%2Bdeb6u1
  • links: PTS, VCS
  • area: main
  • in suites: squeeze-lts
  • size: 17,928 kB
  • ctags: 6,062
  • sloc: python: 44,238; sh: 20,985; tcl: 3,578; ansic: 2,557; lisp: 1,412; makefile: 176; xml: 15
file content (234 lines) | stat: -rwxr-xr-x 8,293 bytes parent folder | download | duplicates (2)
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
#!/usr/bin/env python
#
# check-code - a style and portability checker for Mercurial
#
# Copyright 2010 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import re, glob
import optparse

def repquote(m):
    t = re.sub(r"\w", "x", m.group('text'))
    t = re.sub(r"[^\sx]", "o", t)
    return m.group('quote') + t + m.group('quote')

def reppython(m):
    comment = m.group('comment')
    if comment:
        return "#" * len(comment)
    return repquote(m)

def repcomment(m):
    return m.group(1) + "#" * len(m.group(2))

def repccomment(m):
    t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
    return m.group(1) + t + "*/"

def repcallspaces(m):
    t = re.sub(r"\n\s+", "\n", m.group(2))
    return m.group(1) + t

def repinclude(m):
    return m.group(1) + "<foo>"

def rephere(m):
    t = re.sub(r"\S", "x", m.group(2))
    return m.group(1) + t


testpats = [
    (r'(pushd|popd)', "don't use 'pushd' or 'popd', use 'cd'"),
    (r'\W\$?\(\([^\)]*\)\)', "don't use (()) or $(()), use 'expr'"),
    (r'^function', "don't use 'function', use old style"),
    (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
    (r'echo.*\\n', "don't use 'echo \\n', use printf"),
    (r'echo -n', "don't use 'echo -n', use printf"),
    (r'^diff.*-\w*N', "don't use 'diff -N'"),
    (r'(^| )wc[^|]*$', "filter wc output"),
    (r'head -c', "don't use 'head -c', use 'dd'"),
    (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
    (r'printf.*\\\d\d\d', "don't use 'printf \NNN', use Python"),
    (r'printf.*\\x', "don't use printf \\x, use Python"),
    (r'\$\(.*\)', "don't use $(expr), use `expr`"),
    (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
    (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
     "use egrep for extended grep syntax"),
    (r'/bin/', "don't use explicit paths for tools"),
    (r'\$PWD', "don't use $PWD, use `pwd`"),
    (r'[^\n]\Z', "no trailing newline"),
    (r'export.*=', "don't export and assign at once"),
    ('^([^"\']|("[^"]*")|(\'[^\']*\'))*\\^', "^ must be quoted"),
    (r'^source\b', "don't use 'source', use '.'"),
]

testfilters = [
    (r"( *)(#([^\n]*\S)?)", repcomment),
    (r"<<(\S+)((.|\n)*?\n\1)", rephere),
]

pypats = [
    (r'^\s*\t', "don't use tabs"),
    (r'\S;\s*\n', "semicolon"),
    (r'\w,\w', "missing whitespace after ,"),
    (r'\w[+/*\-<>]\w', "missing whitespace in expression"),
    (r'^\s+\w+=\w+[^,)]$', "missing whitespace in assignment"),
    (r'.{85}', "line too long"),
    (r'[^\n]\Z', "no trailing newline"),
#    (r'^\s+[^_ ][^_. ]+_[^_]+\s*=', "don't use underbars in identifiers"),
#    (r'\w*[a-z][A-Z]\w*\s*=', "don't use camelcase in identifiers"),
    (r'^\s*(if|while|def|class|except|try)\s[^[]*:\s*[^\]#\s]+',
     "linebreak after :"),
    (r'class\s[^(]:', "old-style class, use class foo(object)"),
    (r'^\s+del\(', "del isn't a function"),
    (r'^\s+except\(', "except isn't a function"),
    (r',]', "unneeded trailing ',' in list"),
#    (r'class\s[A-Z][^\(]*\((?!Exception)',
#     "don't capitalize non-exception classes"),
#    (r'in range\(', "use xrange"),
#    (r'^\s*print\s+', "avoid using print in core and extensions"),
    (r'[\x80-\xff]', "non-ASCII character literal"),
    (r'("\')\.format\(', "str.format() not available in Python 2.4"),
    (r'^\s*with\s+', "with not available in Python 2.4"),
    (r'(?<!def)\s+(any|all|format)\(',
     "any/all/format not available in Python 2.4"),
    (r'(?<!def)\s+(callable)\(',
     "callable not available in Python 3, use hasattr(f, '__call__')"),
    (r'if\s.*\selse', "if ... else form not available in Python 2.4"),
    (r'([\(\[]\s\S)|(\S\s[\)\]])', "gratuitous whitespace in () or []"),
#    (r'\s\s=', "gratuitous whitespace before ="),
    (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=)\S',
     "missing whitespace around operator"),
    (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=)\s',
     "missing whitespace around operator"),
    (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=)\S',
     "missing whitespace around operator"),
    (r'[^+=*!<>&| -](\s=|=\s)[^= ]',
     "wrong whitespace around ="),
    (r'raise Exception', "don't raise generic exceptions"),
    (r'ui\.(status|progress|write|note|warn)\([\'\"]x',
     "warning: unwrapped ui message"),
]

pyfilters = [
    (r"""(?msx)(?P<comment>\#.*?$)|
         ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
          (?P<text>(([^\\]|\\.)*?))
          (?P=quote))""", reppython),
]

cpats = [
    (r'//', "don't use //-style comments"),
    (r'^  ', "don't use spaces to indent"),
    (r'\S\t', "don't use tabs except for indent"),
    (r'(\S\s+|^\s+)\n', "trailing whitespace"),
    (r'.{85}', "line too long"),
    (r'(while|if|do|for)\(', "use space after while/if/do/for"),
    (r'return\(', "return is not a function"),
    (r' ;', "no space before ;"),
    (r'\w+\* \w+', "use int *foo, not int* foo"),
    (r'\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
    (r'\S+ (\+\+|--)', "use foo++, not foo ++"),
    (r'\w,\w', "missing whitespace after ,"),
    (r'\w[+/*]\w', "missing whitespace in expression"),
    (r'^#\s+\w', "use #foo, not # foo"),
    (r'[^\n]\Z', "no trailing newline"),
]

cfilters = [
    (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
    (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
    (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
    (r'(\()([^)]+\))', repcallspaces),
]

checks = [
    ('python', r'.*\.(py|cgi)$', pyfilters, pypats),
    ('test script', r'(.*/)?test-[^.~]*$', testfilters, testpats),
    ('c', r'.*\.c$', cfilters, cpats),
]

class norepeatlogger(object):
    def __init__(self):
        self._lastseen = None

    def log(self, fname, lineno, line, msg):
        """print error related a to given line of a given file.

        The faulty line will also be printed but only once in the case
        of multiple errors.

        :fname: filename
        :lineno: line number
        :line: actual content of the line
        :msg: error message
        """
        msgid = fname, lineno, line
        if msgid != self._lastseen:
            print "%s:%d:" % (fname, lineno)
            print " > %s" % line
            self._lastseen = msgid
        print " " + msg

_defaultlogger = norepeatlogger()

def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False):
    """checks style and portability of a given file

    :f: filepath
    :logfunc: function used to report error
              logfunc(filename, linenumber, linecontent, errormessage)
    :maxerr: number of error to display before arborting.
             Set to None (default) to report all errors

    return True if no error is found, False otherwise.
    """
    result = True
    for name, match, filters, pats in checks:
        fc = 0
        if not re.match(match, f):
            continue
        pre = post = open(f).read()
        if "no-" + "check-code" in pre:
            break
        for p, r in filters:
            post = re.sub(p, r, post)
        # print post # uncomment to show filtered version
        z = enumerate(zip(pre.splitlines(), post.splitlines(True)))
        for n, l in z:
            if "check-code" + "-ignore" in l[0]:
                continue
            for p, msg in pats:
                if not warnings and msg.startswith("warning"):
                    continue
                if re.search(p, l[1]):
                    logfunc(f, n + 1, l[0], msg)
                    fc += 1
                    result = False
            if maxerr is not None and fc >= maxerr:
                print " (too many errors, giving up)"
                break
        break
    return result


if __name__ == "__main__":
    parser = optparse.OptionParser("%prog [options] [files]")
    parser.add_option("-w", "--warnings", action="store_true",
                      help="include warning-level checks")
    parser.add_option("-p", "--per-file", type="int",
                      help="max warnings per file")

    parser.set_defaults(per_file=15, warnings=False)
    (options, args) = parser.parse_args()

    if len(args) == 0:
        check = glob.glob("*")
    else:
        check = args

    for f in check:
        checkfile(f, maxerr=options.per_file, warnings=options.warnings)