Show More
@@ -1,454 +1,454 b'' | |||||
1 | #!/usr/bin/env python |
|
1 | #!/usr/bin/env python | |
2 | # |
|
2 | # | |
3 | # check-code - a style and portability checker for Mercurial |
|
3 | # check-code - a style and portability checker for Mercurial | |
4 | # |
|
4 | # | |
5 | # Copyright 2010 Matt Mackall <mpm@selenic.com> |
|
5 | # Copyright 2010 Matt Mackall <mpm@selenic.com> | |
6 | # |
|
6 | # | |
7 | # This software may be used and distributed according to the terms of the |
|
7 | # This software may be used and distributed according to the terms of the | |
8 | # GNU General Public License version 2 or any later version. |
|
8 | # GNU General Public License version 2 or any later version. | |
9 |
|
9 | |||
10 | import re, glob, os, sys |
|
10 | import re, glob, os, sys | |
11 | import keyword |
|
11 | import keyword | |
12 | import optparse |
|
12 | import optparse | |
13 |
|
13 | |||
14 | def repquote(m): |
|
14 | def repquote(m): | |
15 | t = re.sub(r"\w", "x", m.group('text')) |
|
15 | t = re.sub(r"\w", "x", m.group('text')) | |
16 | t = re.sub(r"[^\s\nx]", "o", t) |
|
16 | t = re.sub(r"[^\s\nx]", "o", t) | |
17 | return m.group('quote') + t + m.group('quote') |
|
17 | return m.group('quote') + t + m.group('quote') | |
18 |
|
18 | |||
19 | def reppython(m): |
|
19 | def reppython(m): | |
20 | comment = m.group('comment') |
|
20 | comment = m.group('comment') | |
21 | if comment: |
|
21 | if comment: | |
22 | return "#" * len(comment) |
|
22 | return "#" * len(comment) | |
23 | return repquote(m) |
|
23 | return repquote(m) | |
24 |
|
24 | |||
25 | def repcomment(m): |
|
25 | def repcomment(m): | |
26 | return m.group(1) + "#" * len(m.group(2)) |
|
26 | return m.group(1) + "#" * len(m.group(2)) | |
27 |
|
27 | |||
28 | def repccomment(m): |
|
28 | def repccomment(m): | |
29 | t = re.sub(r"((?<=\n) )|\S", "x", m.group(2)) |
|
29 | t = re.sub(r"((?<=\n) )|\S", "x", m.group(2)) | |
30 | return m.group(1) + t + "*/" |
|
30 | return m.group(1) + t + "*/" | |
31 |
|
31 | |||
32 | def repcallspaces(m): |
|
32 | def repcallspaces(m): | |
33 | t = re.sub(r"\n\s+", "\n", m.group(2)) |
|
33 | t = re.sub(r"\n\s+", "\n", m.group(2)) | |
34 | return m.group(1) + t |
|
34 | return m.group(1) + t | |
35 |
|
35 | |||
36 | def repinclude(m): |
|
36 | def repinclude(m): | |
37 | return m.group(1) + "<foo>" |
|
37 | return m.group(1) + "<foo>" | |
38 |
|
38 | |||
39 | def rephere(m): |
|
39 | def rephere(m): | |
40 | t = re.sub(r"\S", "x", m.group(2)) |
|
40 | t = re.sub(r"\S", "x", m.group(2)) | |
41 | return m.group(1) + t |
|
41 | return m.group(1) + t | |
42 |
|
42 | |||
43 |
|
43 | |||
44 | testpats = [ |
|
44 | testpats = [ | |
45 | [ |
|
45 | [ | |
46 | (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"), |
|
46 | (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"), | |
47 | (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"), |
|
47 | (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"), | |
48 | (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"), |
|
48 | (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"), | |
49 | (r'sed.*-i', "don't use 'sed -i', use a temporary file"), |
|
49 | (r'sed.*-i', "don't use 'sed -i', use a temporary file"), | |
50 | (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"), |
|
50 | (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"), | |
51 | (r'echo -n', "don't use 'echo -n', use printf"), |
|
51 | (r'echo -n', "don't use 'echo -n', use printf"), | |
52 | (r'(^| )wc[^|]*$\n(?!.*\(re\))', "filter wc output"), |
|
52 | (r'(^| )wc[^|]*$\n(?!.*\(re\))', "filter wc output"), | |
53 | (r'head -c', "don't use 'head -c', use 'dd'"), |
|
53 | (r'head -c', "don't use 'head -c', use 'dd'"), | |
54 | (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"), |
|
54 | (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"), | |
55 | (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"), |
|
55 | (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"), | |
56 | (r'printf.*\\([1-9]|0\d)', "don't use 'printf \NNN', use Python"), |
|
56 | (r'printf.*\\([1-9]|0\d)', "don't use 'printf \NNN', use Python"), | |
57 | (r'printf.*\\x', "don't use printf \\x, use Python"), |
|
57 | (r'printf.*\\x', "don't use printf \\x, use Python"), | |
58 | (r'\$\(.*\)', "don't use $(expr), use `expr`"), |
|
58 | (r'\$\(.*\)', "don't use $(expr), use `expr`"), | |
59 | (r'rm -rf \*', "don't use naked rm -rf, target a directory"), |
|
59 | (r'rm -rf \*', "don't use naked rm -rf, target a directory"), | |
60 | (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w', |
|
60 | (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w', | |
61 | "use egrep for extended grep syntax"), |
|
61 | "use egrep for extended grep syntax"), | |
62 | (r'/bin/', "don't use explicit paths for tools"), |
|
62 | (r'/bin/', "don't use explicit paths for tools"), | |
63 | (r'[^\n]\Z', "no trailing newline"), |
|
63 | (r'[^\n]\Z', "no trailing newline"), | |
64 | (r'export.*=', "don't export and assign at once"), |
|
64 | (r'export.*=', "don't export and assign at once"), | |
65 | (r'^source\b', "don't use 'source', use '.'"), |
|
65 | (r'^source\b', "don't use 'source', use '.'"), | |
66 | (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"), |
|
66 | (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"), | |
67 | (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"), |
|
67 | (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"), | |
68 | (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"), |
|
68 | (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"), | |
69 | (r'^stop\(\)', "don't use 'stop' as a shell function name"), |
|
69 | (r'^stop\(\)', "don't use 'stop' as a shell function name"), | |
70 | (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"), |
|
70 | (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"), | |
71 | (r'^alias\b.*=', "don't use alias, use a function"), |
|
71 | (r'^alias\b.*=', "don't use alias, use a function"), | |
72 | (r'if\s*!', "don't use '!' to negate exit status"), |
|
72 | (r'if\s*!', "don't use '!' to negate exit status"), | |
73 | (r'/dev/u?random', "don't use entropy, use /dev/zero"), |
|
73 | (r'/dev/u?random', "don't use entropy, use /dev/zero"), | |
74 | (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"), |
|
74 | (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"), | |
75 | (r'^( *)\t', "don't use tabs to indent"), |
|
75 | (r'^( *)\t', "don't use tabs to indent"), | |
76 | ], |
|
76 | ], | |
77 | # warnings |
|
77 | # warnings | |
78 | [ |
|
78 | [ | |
79 | (r'^function', "don't use 'function', use old style"), |
|
79 | (r'^function', "don't use 'function', use old style"), | |
80 | (r'^diff.*-\w*N', "don't use 'diff -N'"), |
|
80 | (r'^diff.*-\w*N', "don't use 'diff -N'"), | |
81 | (r'\$PWD', "don't use $PWD, use `pwd`"), |
|
81 | (r'\$PWD', "don't use $PWD, use `pwd`"), | |
82 | (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"), |
|
82 | (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"), | |
83 | ] |
|
83 | ] | |
84 | ] |
|
84 | ] | |
85 |
|
85 | |||
86 | testfilters = [ |
|
86 | testfilters = [ | |
87 | (r"( *)(#([^\n]*\S)?)", repcomment), |
|
87 | (r"( *)(#([^\n]*\S)?)", repcomment), | |
88 | (r"<<(\S+)((.|\n)*?\n\1)", rephere), |
|
88 | (r"<<(\S+)((.|\n)*?\n\1)", rephere), | |
89 | ] |
|
89 | ] | |
90 |
|
90 | |||
91 | uprefix = r"^ \$ " |
|
91 | uprefix = r"^ \$ " | |
92 | utestpats = [ |
|
92 | utestpats = [ | |
93 | [ |
|
93 | [ | |
94 | (r'^(\S.*|| [$>] .*)[ \t]\n', "trailing whitespace on non-output"), |
|
94 | (r'^(\S.*|| [$>] .*)[ \t]\n', "trailing whitespace on non-output"), | |
95 | (uprefix + r'.*\|\s*sed[^|>\n]*\n', |
|
95 | (uprefix + r'.*\|\s*sed[^|>\n]*\n', | |
96 | "use regex test output patterns instead of sed"), |
|
96 | "use regex test output patterns instead of sed"), | |
97 | (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"), |
|
97 | (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"), | |
98 | (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"), |
|
98 | (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"), | |
99 | (uprefix + r'.*\|\| echo.*(fail|error)', |
|
99 | (uprefix + r'.*\|\| echo.*(fail|error)', | |
100 | "explicit exit code checks unnecessary"), |
|
100 | "explicit exit code checks unnecessary"), | |
101 | (uprefix + r'set -e', "don't use set -e"), |
|
101 | (uprefix + r'set -e', "don't use set -e"), | |
102 | (uprefix + r'\s', "don't indent commands, use > for continued lines"), |
|
102 | (uprefix + r'\s', "don't indent commands, use > for continued lines"), | |
103 | (r'^ saved backup bundle to \$TESTTMP.*\.hg$', |
|
103 | (r'^ saved backup bundle to \$TESTTMP.*\.hg$', | |
104 | "use (glob) to match Windows paths too"), |
|
104 | "use (glob) to match Windows paths too"), | |
105 | ], |
|
105 | ], | |
106 | # warnings |
|
106 | # warnings | |
107 | [] |
|
107 | [] | |
108 | ] |
|
108 | ] | |
109 |
|
109 | |||
110 | for i in [0, 1]: |
|
110 | for i in [0, 1]: | |
111 | for p, m in testpats[i]: |
|
111 | for p, m in testpats[i]: | |
112 | if p.startswith(r'^'): |
|
112 | if p.startswith(r'^'): | |
113 | p = r"^ [$>] (%s)" % p[1:] |
|
113 | p = r"^ [$>] (%s)" % p[1:] | |
114 | else: |
|
114 | else: | |
115 | p = r"^ [$>] .*(%s)" % p |
|
115 | p = r"^ [$>] .*(%s)" % p | |
116 | utestpats[i].append((p, m)) |
|
116 | utestpats[i].append((p, m)) | |
117 |
|
117 | |||
118 | utestfilters = [ |
|
118 | utestfilters = [ | |
119 | (r"<<(\S+)((.|\n)*?\n > \1)", rephere), |
|
119 | (r"<<(\S+)((.|\n)*?\n > \1)", rephere), | |
120 | (r"( *)(#([^\n]*\S)?)", repcomment), |
|
120 | (r"( *)(#([^\n]*\S)?)", repcomment), | |
121 | ] |
|
121 | ] | |
122 |
|
122 | |||
123 | pypats = [ |
|
123 | pypats = [ | |
124 | [ |
|
124 | [ | |
125 | (r'^\s*def\s*\w+\s*\(.*,\s*\(', |
|
125 | (r'^\s*def\s*\w+\s*\(.*,\s*\(', | |
126 | "tuple parameter unpacking not available in Python 3+"), |
|
126 | "tuple parameter unpacking not available in Python 3+"), | |
127 | (r'lambda\s*\(.*,.*\)', |
|
127 | (r'lambda\s*\(.*,.*\)', | |
128 | "tuple parameter unpacking not available in Python 3+"), |
|
128 | "tuple parameter unpacking not available in Python 3+"), | |
129 | (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"), |
|
129 | (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"), | |
130 | (r'\breduce\s*\(.*', "reduce is not available in Python 3+"), |
|
130 | (r'\breduce\s*\(.*', "reduce is not available in Python 3+"), | |
131 | (r'\.has_key\b', "dict.has_key is not available in Python 3+"), |
|
131 | (r'\.has_key\b', "dict.has_key is not available in Python 3+"), | |
132 | (r'^\s*\t', "don't use tabs"), |
|
132 | (r'^\s*\t', "don't use tabs"), | |
133 | (r'\S;\s*\n', "semicolon"), |
|
133 | (r'\S;\s*\n', "semicolon"), | |
134 | (r'[^_]_\("[^"]+"\s*%', "don't use % inside _()"), |
|
134 | (r'[^_]_\("[^"]+"\s*%', "don't use % inside _()"), | |
135 | (r"[^_]_\('[^']+'\s*%", "don't use % inside _()"), |
|
135 | (r"[^_]_\('[^']+'\s*%", "don't use % inside _()"), | |
136 | (r'(\w|\)),\w', "missing whitespace after ,"), |
|
136 | (r'(\w|\)),\w', "missing whitespace after ,"), | |
137 | (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"), |
|
137 | (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"), | |
138 |
(r'^\s+\w |
|
138 | (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"), | |
139 | (r'(\s+)try:\n((?:\n|\1\s.*\n)+?)\1except.*?:\n' |
|
139 | (r'(\s+)try:\n((?:\n|\1\s.*\n)+?)\1except.*?:\n' | |
140 | r'((?:\n|\1\s.*\n)+?)\1finally:', 'no try/except/finally in Python 2.4'), |
|
140 | r'((?:\n|\1\s.*\n)+?)\1finally:', 'no try/except/finally in Python 2.4'), | |
141 | (r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?' |
|
141 | (r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?' | |
142 | r'((?:\n|\1\s.*\n)+?)\1finally:', |
|
142 | r'((?:\n|\1\s.*\n)+?)\1finally:', | |
143 | 'no yield inside try/finally in Python 2.4'), |
|
143 | 'no yield inside try/finally in Python 2.4'), | |
144 | (r'.{81}', "line too long"), |
|
144 | (r'.{81}', "line too long"), | |
145 | (r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'), |
|
145 | (r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'), | |
146 | (r'[^\n]\Z', "no trailing newline"), |
|
146 | (r'[^\n]\Z', "no trailing newline"), | |
147 | (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"), |
|
147 | (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"), | |
148 | # (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=', |
|
148 | # (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=', | |
149 | # "don't use underbars in identifiers"), |
|
149 | # "don't use underbars in identifiers"), | |
150 | (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ', |
|
150 | (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ', | |
151 | "don't use camelcase in identifiers"), |
|
151 | "don't use camelcase in identifiers"), | |
152 | (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+', |
|
152 | (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+', | |
153 | "linebreak after :"), |
|
153 | "linebreak after :"), | |
154 | (r'class\s[^( \n]+:', "old-style class, use class foo(object)"), |
|
154 | (r'class\s[^( \n]+:', "old-style class, use class foo(object)"), | |
155 | (r'class\s[^( \n]+\(\):', |
|
155 | (r'class\s[^( \n]+\(\):', | |
156 | "class foo() not available in Python 2.4, use class foo(object)"), |
|
156 | "class foo() not available in Python 2.4, use class foo(object)"), | |
157 | (r'\b(%s)\(' % '|'.join(keyword.kwlist), |
|
157 | (r'\b(%s)\(' % '|'.join(keyword.kwlist), | |
158 | "Python keyword is not a function"), |
|
158 | "Python keyword is not a function"), | |
159 | (r',]', "unneeded trailing ',' in list"), |
|
159 | (r',]', "unneeded trailing ',' in list"), | |
160 | # (r'class\s[A-Z][^\(]*\((?!Exception)', |
|
160 | # (r'class\s[A-Z][^\(]*\((?!Exception)', | |
161 | # "don't capitalize non-exception classes"), |
|
161 | # "don't capitalize non-exception classes"), | |
162 | # (r'in range\(', "use xrange"), |
|
162 | # (r'in range\(', "use xrange"), | |
163 | # (r'^\s*print\s+', "avoid using print in core and extensions"), |
|
163 | # (r'^\s*print\s+', "avoid using print in core and extensions"), | |
164 | (r'[\x80-\xff]', "non-ASCII character literal"), |
|
164 | (r'[\x80-\xff]', "non-ASCII character literal"), | |
165 | (r'("\')\.format\(', "str.format() not available in Python 2.4"), |
|
165 | (r'("\')\.format\(', "str.format() not available in Python 2.4"), | |
166 | (r'^\s*with\s+', "with not available in Python 2.4"), |
|
166 | (r'^\s*with\s+', "with not available in Python 2.4"), | |
167 | (r'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"), |
|
167 | (r'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"), | |
168 | (r'^\s*except.* as .*:', "except as not available in Python 2.4"), |
|
168 | (r'^\s*except.* as .*:', "except as not available in Python 2.4"), | |
169 | (r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"), |
|
169 | (r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"), | |
170 | (r'(?<!def)\s+(any|all|format)\(', |
|
170 | (r'(?<!def)\s+(any|all|format)\(', | |
171 | "any/all/format not available in Python 2.4"), |
|
171 | "any/all/format not available in Python 2.4"), | |
172 | (r'(?<!def)\s+(callable)\(', |
|
172 | (r'(?<!def)\s+(callable)\(', | |
173 | "callable not available in Python 3, use getattr(f, '__call__', None)"), |
|
173 | "callable not available in Python 3, use getattr(f, '__call__', None)"), | |
174 | (r'if\s.*\selse', "if ... else form not available in Python 2.4"), |
|
174 | (r'if\s.*\selse', "if ... else form not available in Python 2.4"), | |
175 | (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist), |
|
175 | (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist), | |
176 | "gratuitous whitespace after Python keyword"), |
|
176 | "gratuitous whitespace after Python keyword"), | |
177 | (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"), |
|
177 | (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"), | |
178 | # (r'\s\s=', "gratuitous whitespace before ="), |
|
178 | # (r'\s\s=', "gratuitous whitespace before ="), | |
179 | (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S', |
|
179 | (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S', | |
180 | "missing whitespace around operator"), |
|
180 | "missing whitespace around operator"), | |
181 | (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s', |
|
181 | (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s', | |
182 | "missing whitespace around operator"), |
|
182 | "missing whitespace around operator"), | |
183 | (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S', |
|
183 | (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S', | |
184 | "missing whitespace around operator"), |
|
184 | "missing whitespace around operator"), | |
185 | (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]', |
|
185 | (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]', | |
186 | "wrong whitespace around ="), |
|
186 | "wrong whitespace around ="), | |
187 | (r'raise Exception', "don't raise generic exceptions"), |
|
187 | (r'raise Exception', "don't raise generic exceptions"), | |
188 | (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"), |
|
188 | (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"), | |
189 | (r' [=!]=\s+(True|False|None)', |
|
189 | (r' [=!]=\s+(True|False|None)', | |
190 | "comparison with singleton, use 'is' or 'is not' instead"), |
|
190 | "comparison with singleton, use 'is' or 'is not' instead"), | |
191 | (r'^\s*(while|if) [01]:', |
|
191 | (r'^\s*(while|if) [01]:', | |
192 | "use True/False for constant Boolean expression"), |
|
192 | "use True/False for constant Boolean expression"), | |
193 | (r'(?:(?<!def)\s+|\()hasattr', |
|
193 | (r'(?:(?<!def)\s+|\()hasattr', | |
194 | 'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'), |
|
194 | 'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'), | |
195 | (r'opener\([^)]*\).read\(', |
|
195 | (r'opener\([^)]*\).read\(', | |
196 | "use opener.read() instead"), |
|
196 | "use opener.read() instead"), | |
197 | (r'BaseException', 'not in Python 2.4, use Exception'), |
|
197 | (r'BaseException', 'not in Python 2.4, use Exception'), | |
198 | (r'os\.path\.relpath', 'os.path.relpath is not in Python 2.5'), |
|
198 | (r'os\.path\.relpath', 'os.path.relpath is not in Python 2.5'), | |
199 | (r'opener\([^)]*\).write\(', |
|
199 | (r'opener\([^)]*\).write\(', | |
200 | "use opener.write() instead"), |
|
200 | "use opener.write() instead"), | |
201 | (r'[\s\(](open|file)\([^)]*\)\.read\(', |
|
201 | (r'[\s\(](open|file)\([^)]*\)\.read\(', | |
202 | "use util.readfile() instead"), |
|
202 | "use util.readfile() instead"), | |
203 | (r'[\s\(](open|file)\([^)]*\)\.write\(', |
|
203 | (r'[\s\(](open|file)\([^)]*\)\.write\(', | |
204 | "use util.readfile() instead"), |
|
204 | "use util.readfile() instead"), | |
205 | (r'^[\s\(]*(open(er)?|file)\([^)]*\)', |
|
205 | (r'^[\s\(]*(open(er)?|file)\([^)]*\)', | |
206 | "always assign an opened file to a variable, and close it afterwards"), |
|
206 | "always assign an opened file to a variable, and close it afterwards"), | |
207 | (r'[\s\(](open|file)\([^)]*\)\.', |
|
207 | (r'[\s\(](open|file)\([^)]*\)\.', | |
208 | "always assign an opened file to a variable, and close it afterwards"), |
|
208 | "always assign an opened file to a variable, and close it afterwards"), | |
209 | (r'(?i)descendent', "the proper spelling is descendAnt"), |
|
209 | (r'(?i)descendent', "the proper spelling is descendAnt"), | |
210 | (r'\.debug\(\_', "don't mark debug messages for translation"), |
|
210 | (r'\.debug\(\_', "don't mark debug messages for translation"), | |
211 | (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"), |
|
211 | (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"), | |
212 | (r'^\s*except\s*:', "warning: naked except clause", r'#.*re-raises'), |
|
212 | (r'^\s*except\s*:', "warning: naked except clause", r'#.*re-raises'), | |
213 | (r':\n( )*( ){1,3}[^ ]', "must indent 4 spaces"), |
|
213 | (r':\n( )*( ){1,3}[^ ]', "must indent 4 spaces"), | |
214 | (r'ui\.(status|progress|write|note|warn)\([\'\"]x', |
|
214 | (r'ui\.(status|progress|write|note|warn)\([\'\"]x', | |
215 | "missing _() in ui message (use () to hide false-positives)"), |
|
215 | "missing _() in ui message (use () to hide false-positives)"), | |
216 | ], |
|
216 | ], | |
217 | # warnings |
|
217 | # warnings | |
218 | [ |
|
218 | [ | |
219 | ] |
|
219 | ] | |
220 | ] |
|
220 | ] | |
221 |
|
221 | |||
222 | pyfilters = [ |
|
222 | pyfilters = [ | |
223 | (r"""(?msx)(?P<comment>\#.*?$)| |
|
223 | (r"""(?msx)(?P<comment>\#.*?$)| | |
224 | ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!"))) |
|
224 | ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!"))) | |
225 | (?P<text>(([^\\]|\\.)*?)) |
|
225 | (?P<text>(([^\\]|\\.)*?)) | |
226 | (?P=quote))""", reppython), |
|
226 | (?P=quote))""", reppython), | |
227 | ] |
|
227 | ] | |
228 |
|
228 | |||
229 | cpats = [ |
|
229 | cpats = [ | |
230 | [ |
|
230 | [ | |
231 | (r'//', "don't use //-style comments"), |
|
231 | (r'//', "don't use //-style comments"), | |
232 | (r'^ ', "don't use spaces to indent"), |
|
232 | (r'^ ', "don't use spaces to indent"), | |
233 | (r'\S\t', "don't use tabs except for indent"), |
|
233 | (r'\S\t', "don't use tabs except for indent"), | |
234 | (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"), |
|
234 | (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"), | |
235 | (r'.{81}', "line too long"), |
|
235 | (r'.{81}', "line too long"), | |
236 | (r'(while|if|do|for)\(', "use space after while/if/do/for"), |
|
236 | (r'(while|if|do|for)\(', "use space after while/if/do/for"), | |
237 | (r'return\(', "return is not a function"), |
|
237 | (r'return\(', "return is not a function"), | |
238 | (r' ;', "no space before ;"), |
|
238 | (r' ;', "no space before ;"), | |
239 | (r'\w+\* \w+', "use int *foo, not int* foo"), |
|
239 | (r'\w+\* \w+', "use int *foo, not int* foo"), | |
240 | (r'\([^\)]+\) \w+', "use (int)foo, not (int) foo"), |
|
240 | (r'\([^\)]+\) \w+', "use (int)foo, not (int) foo"), | |
241 | (r'\w+ (\+\+|--)', "use foo++, not foo ++"), |
|
241 | (r'\w+ (\+\+|--)', "use foo++, not foo ++"), | |
242 | (r'\w,\w', "missing whitespace after ,"), |
|
242 | (r'\w,\w', "missing whitespace after ,"), | |
243 | (r'^[^#]\w[+/*]\w', "missing whitespace in expression"), |
|
243 | (r'^[^#]\w[+/*]\w', "missing whitespace in expression"), | |
244 | (r'^#\s+\w', "use #foo, not # foo"), |
|
244 | (r'^#\s+\w', "use #foo, not # foo"), | |
245 | (r'[^\n]\Z', "no trailing newline"), |
|
245 | (r'[^\n]\Z', "no trailing newline"), | |
246 | (r'^\s*#import\b', "use only #include in standard C code"), |
|
246 | (r'^\s*#import\b', "use only #include in standard C code"), | |
247 | ], |
|
247 | ], | |
248 | # warnings |
|
248 | # warnings | |
249 | [] |
|
249 | [] | |
250 | ] |
|
250 | ] | |
251 |
|
251 | |||
252 | cfilters = [ |
|
252 | cfilters = [ | |
253 | (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment), |
|
253 | (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment), | |
254 | (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote), |
|
254 | (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote), | |
255 | (r'''(#\s*include\s+<)([^>]+)>''', repinclude), |
|
255 | (r'''(#\s*include\s+<)([^>]+)>''', repinclude), | |
256 | (r'(\()([^)]+\))', repcallspaces), |
|
256 | (r'(\()([^)]+\))', repcallspaces), | |
257 | ] |
|
257 | ] | |
258 |
|
258 | |||
259 | inutilpats = [ |
|
259 | inutilpats = [ | |
260 | [ |
|
260 | [ | |
261 | (r'\bui\.', "don't use ui in util"), |
|
261 | (r'\bui\.', "don't use ui in util"), | |
262 | ], |
|
262 | ], | |
263 | # warnings |
|
263 | # warnings | |
264 | [] |
|
264 | [] | |
265 | ] |
|
265 | ] | |
266 |
|
266 | |||
267 | inrevlogpats = [ |
|
267 | inrevlogpats = [ | |
268 | [ |
|
268 | [ | |
269 | (r'\brepo\.', "don't use repo in revlog"), |
|
269 | (r'\brepo\.', "don't use repo in revlog"), | |
270 | ], |
|
270 | ], | |
271 | # warnings |
|
271 | # warnings | |
272 | [] |
|
272 | [] | |
273 | ] |
|
273 | ] | |
274 |
|
274 | |||
275 | checks = [ |
|
275 | checks = [ | |
276 | ('python', r'.*\.(py|cgi)$', pyfilters, pypats), |
|
276 | ('python', r'.*\.(py|cgi)$', pyfilters, pypats), | |
277 | ('test script', r'(.*/)?test-[^.~]*$', testfilters, testpats), |
|
277 | ('test script', r'(.*/)?test-[^.~]*$', testfilters, testpats), | |
278 | ('c', r'.*\.c$', cfilters, cpats), |
|
278 | ('c', r'.*\.c$', cfilters, cpats), | |
279 | ('unified test', r'.*\.t$', utestfilters, utestpats), |
|
279 | ('unified test', r'.*\.t$', utestfilters, utestpats), | |
280 | ('layering violation repo in revlog', r'mercurial/revlog\.py', pyfilters, |
|
280 | ('layering violation repo in revlog', r'mercurial/revlog\.py', pyfilters, | |
281 | inrevlogpats), |
|
281 | inrevlogpats), | |
282 | ('layering violation ui in util', r'mercurial/util\.py', pyfilters, |
|
282 | ('layering violation ui in util', r'mercurial/util\.py', pyfilters, | |
283 | inutilpats), |
|
283 | inutilpats), | |
284 | ] |
|
284 | ] | |
285 |
|
285 | |||
286 | class norepeatlogger(object): |
|
286 | class norepeatlogger(object): | |
287 | def __init__(self): |
|
287 | def __init__(self): | |
288 | self._lastseen = None |
|
288 | self._lastseen = None | |
289 |
|
289 | |||
290 | def log(self, fname, lineno, line, msg, blame): |
|
290 | def log(self, fname, lineno, line, msg, blame): | |
291 | """print error related a to given line of a given file. |
|
291 | """print error related a to given line of a given file. | |
292 |
|
292 | |||
293 | The faulty line will also be printed but only once in the case |
|
293 | The faulty line will also be printed but only once in the case | |
294 | of multiple errors. |
|
294 | of multiple errors. | |
295 |
|
295 | |||
296 | :fname: filename |
|
296 | :fname: filename | |
297 | :lineno: line number |
|
297 | :lineno: line number | |
298 | :line: actual content of the line |
|
298 | :line: actual content of the line | |
299 | :msg: error message |
|
299 | :msg: error message | |
300 | """ |
|
300 | """ | |
301 | msgid = fname, lineno, line |
|
301 | msgid = fname, lineno, line | |
302 | if msgid != self._lastseen: |
|
302 | if msgid != self._lastseen: | |
303 | if blame: |
|
303 | if blame: | |
304 | print "%s:%d (%s):" % (fname, lineno, blame) |
|
304 | print "%s:%d (%s):" % (fname, lineno, blame) | |
305 | else: |
|
305 | else: | |
306 | print "%s:%d:" % (fname, lineno) |
|
306 | print "%s:%d:" % (fname, lineno) | |
307 | print " > %s" % line |
|
307 | print " > %s" % line | |
308 | self._lastseen = msgid |
|
308 | self._lastseen = msgid | |
309 | print " " + msg |
|
309 | print " " + msg | |
310 |
|
310 | |||
311 | _defaultlogger = norepeatlogger() |
|
311 | _defaultlogger = norepeatlogger() | |
312 |
|
312 | |||
313 | def getblame(f): |
|
313 | def getblame(f): | |
314 | lines = [] |
|
314 | lines = [] | |
315 | for l in os.popen('hg annotate -un %s' % f): |
|
315 | for l in os.popen('hg annotate -un %s' % f): | |
316 | start, line = l.split(':', 1) |
|
316 | start, line = l.split(':', 1) | |
317 | user, rev = start.split() |
|
317 | user, rev = start.split() | |
318 | lines.append((line[1:-1], user, rev)) |
|
318 | lines.append((line[1:-1], user, rev)) | |
319 | return lines |
|
319 | return lines | |
320 |
|
320 | |||
321 | def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False, |
|
321 | def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False, | |
322 | blame=False, debug=False, lineno=True): |
|
322 | blame=False, debug=False, lineno=True): | |
323 | """checks style and portability of a given file |
|
323 | """checks style and portability of a given file | |
324 |
|
324 | |||
325 | :f: filepath |
|
325 | :f: filepath | |
326 | :logfunc: function used to report error |
|
326 | :logfunc: function used to report error | |
327 | logfunc(filename, linenumber, linecontent, errormessage) |
|
327 | logfunc(filename, linenumber, linecontent, errormessage) | |
328 | :maxerr: number of error to display before aborting. |
|
328 | :maxerr: number of error to display before aborting. | |
329 | Set to false (default) to report all errors |
|
329 | Set to false (default) to report all errors | |
330 |
|
330 | |||
331 | return True if no error is found, False otherwise. |
|
331 | return True if no error is found, False otherwise. | |
332 | """ |
|
332 | """ | |
333 | blamecache = None |
|
333 | blamecache = None | |
334 | result = True |
|
334 | result = True | |
335 | for name, match, filters, pats in checks: |
|
335 | for name, match, filters, pats in checks: | |
336 | if debug: |
|
336 | if debug: | |
337 | print name, f |
|
337 | print name, f | |
338 | fc = 0 |
|
338 | fc = 0 | |
339 | if not re.match(match, f): |
|
339 | if not re.match(match, f): | |
340 | if debug: |
|
340 | if debug: | |
341 | print "Skipping %s for %s it doesn't match %s" % ( |
|
341 | print "Skipping %s for %s it doesn't match %s" % ( | |
342 | name, match, f) |
|
342 | name, match, f) | |
343 | continue |
|
343 | continue | |
344 | fp = open(f) |
|
344 | fp = open(f) | |
345 | pre = post = fp.read() |
|
345 | pre = post = fp.read() | |
346 | fp.close() |
|
346 | fp.close() | |
347 | if "no-" + "check-code" in pre: |
|
347 | if "no-" + "check-code" in pre: | |
348 | if debug: |
|
348 | if debug: | |
349 | print "Skipping %s for %s it has no- and check-code" % ( |
|
349 | print "Skipping %s for %s it has no- and check-code" % ( | |
350 | name, f) |
|
350 | name, f) | |
351 | break |
|
351 | break | |
352 | for p, r in filters: |
|
352 | for p, r in filters: | |
353 | post = re.sub(p, r, post) |
|
353 | post = re.sub(p, r, post) | |
354 | if warnings: |
|
354 | if warnings: | |
355 | pats = pats[0] + pats[1] |
|
355 | pats = pats[0] + pats[1] | |
356 | else: |
|
356 | else: | |
357 | pats = pats[0] |
|
357 | pats = pats[0] | |
358 | # print post # uncomment to show filtered version |
|
358 | # print post # uncomment to show filtered version | |
359 |
|
359 | |||
360 | if debug: |
|
360 | if debug: | |
361 | print "Checking %s for %s" % (name, f) |
|
361 | print "Checking %s for %s" % (name, f) | |
362 |
|
362 | |||
363 | prelines = None |
|
363 | prelines = None | |
364 | errors = [] |
|
364 | errors = [] | |
365 | for pat in pats: |
|
365 | for pat in pats: | |
366 | if len(pat) == 3: |
|
366 | if len(pat) == 3: | |
367 | p, msg, ignore = pat |
|
367 | p, msg, ignore = pat | |
368 | else: |
|
368 | else: | |
369 | p, msg = pat |
|
369 | p, msg = pat | |
370 | ignore = None |
|
370 | ignore = None | |
371 |
|
371 | |||
372 | # fix-up regexes for multi-line searches |
|
372 | # fix-up regexes for multi-line searches | |
373 | po = p |
|
373 | po = p | |
374 | # \s doesn't match \n |
|
374 | # \s doesn't match \n | |
375 | p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p) |
|
375 | p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p) | |
376 | # [^...] doesn't match newline |
|
376 | # [^...] doesn't match newline | |
377 | p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p) |
|
377 | p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p) | |
378 |
|
378 | |||
379 | #print po, '=>', p |
|
379 | #print po, '=>', p | |
380 |
|
380 | |||
381 | pos = 0 |
|
381 | pos = 0 | |
382 | n = 0 |
|
382 | n = 0 | |
383 | for m in re.finditer(p, post, re.MULTILINE): |
|
383 | for m in re.finditer(p, post, re.MULTILINE): | |
384 | if prelines is None: |
|
384 | if prelines is None: | |
385 | prelines = pre.splitlines() |
|
385 | prelines = pre.splitlines() | |
386 | postlines = post.splitlines(True) |
|
386 | postlines = post.splitlines(True) | |
387 |
|
387 | |||
388 | start = m.start() |
|
388 | start = m.start() | |
389 | while n < len(postlines): |
|
389 | while n < len(postlines): | |
390 | step = len(postlines[n]) |
|
390 | step = len(postlines[n]) | |
391 | if pos + step > start: |
|
391 | if pos + step > start: | |
392 | break |
|
392 | break | |
393 | pos += step |
|
393 | pos += step | |
394 | n += 1 |
|
394 | n += 1 | |
395 | l = prelines[n] |
|
395 | l = prelines[n] | |
396 |
|
396 | |||
397 | if "check-code" + "-ignore" in l: |
|
397 | if "check-code" + "-ignore" in l: | |
398 | if debug: |
|
398 | if debug: | |
399 | print "Skipping %s for %s:%s (check-code -ignore)" % ( |
|
399 | print "Skipping %s for %s:%s (check-code -ignore)" % ( | |
400 | name, f, n) |
|
400 | name, f, n) | |
401 | continue |
|
401 | continue | |
402 | elif ignore and re.search(ignore, l, re.MULTILINE): |
|
402 | elif ignore and re.search(ignore, l, re.MULTILINE): | |
403 | continue |
|
403 | continue | |
404 | bd = "" |
|
404 | bd = "" | |
405 | if blame: |
|
405 | if blame: | |
406 | bd = 'working directory' |
|
406 | bd = 'working directory' | |
407 | if not blamecache: |
|
407 | if not blamecache: | |
408 | blamecache = getblame(f) |
|
408 | blamecache = getblame(f) | |
409 | if n < len(blamecache): |
|
409 | if n < len(blamecache): | |
410 | bl, bu, br = blamecache[n] |
|
410 | bl, bu, br = blamecache[n] | |
411 | if bl == l: |
|
411 | if bl == l: | |
412 | bd = '%s@%s' % (bu, br) |
|
412 | bd = '%s@%s' % (bu, br) | |
413 | errors.append((f, lineno and n + 1, l, msg, bd)) |
|
413 | errors.append((f, lineno and n + 1, l, msg, bd)) | |
414 | result = False |
|
414 | result = False | |
415 |
|
415 | |||
416 | errors.sort() |
|
416 | errors.sort() | |
417 | for e in errors: |
|
417 | for e in errors: | |
418 | logfunc(*e) |
|
418 | logfunc(*e) | |
419 | fc += 1 |
|
419 | fc += 1 | |
420 | if maxerr and fc >= maxerr: |
|
420 | if maxerr and fc >= maxerr: | |
421 | print " (too many errors, giving up)" |
|
421 | print " (too many errors, giving up)" | |
422 | break |
|
422 | break | |
423 |
|
423 | |||
424 | return result |
|
424 | return result | |
425 |
|
425 | |||
426 | if __name__ == "__main__": |
|
426 | if __name__ == "__main__": | |
427 | parser = optparse.OptionParser("%prog [options] [files]") |
|
427 | parser = optparse.OptionParser("%prog [options] [files]") | |
428 | parser.add_option("-w", "--warnings", action="store_true", |
|
428 | parser.add_option("-w", "--warnings", action="store_true", | |
429 | help="include warning-level checks") |
|
429 | help="include warning-level checks") | |
430 | parser.add_option("-p", "--per-file", type="int", |
|
430 | parser.add_option("-p", "--per-file", type="int", | |
431 | help="max warnings per file") |
|
431 | help="max warnings per file") | |
432 | parser.add_option("-b", "--blame", action="store_true", |
|
432 | parser.add_option("-b", "--blame", action="store_true", | |
433 | help="use annotate to generate blame info") |
|
433 | help="use annotate to generate blame info") | |
434 | parser.add_option("", "--debug", action="store_true", |
|
434 | parser.add_option("", "--debug", action="store_true", | |
435 | help="show debug information") |
|
435 | help="show debug information") | |
436 | parser.add_option("", "--nolineno", action="store_false", |
|
436 | parser.add_option("", "--nolineno", action="store_false", | |
437 | dest='lineno', help="don't show line numbers") |
|
437 | dest='lineno', help="don't show line numbers") | |
438 |
|
438 | |||
439 | parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False, |
|
439 | parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False, | |
440 | lineno=True) |
|
440 | lineno=True) | |
441 | (options, args) = parser.parse_args() |
|
441 | (options, args) = parser.parse_args() | |
442 |
|
442 | |||
443 | if len(args) == 0: |
|
443 | if len(args) == 0: | |
444 | check = glob.glob("*") |
|
444 | check = glob.glob("*") | |
445 | else: |
|
445 | else: | |
446 | check = args |
|
446 | check = args | |
447 |
|
447 | |||
448 | ret = 0 |
|
448 | ret = 0 | |
449 | for f in check: |
|
449 | for f in check: | |
450 | if not checkfile(f, maxerr=options.per_file, warnings=options.warnings, |
|
450 | if not checkfile(f, maxerr=options.per_file, warnings=options.warnings, | |
451 | blame=options.blame, debug=options.debug, |
|
451 | blame=options.blame, debug=options.debug, | |
452 | lineno=options.lineno): |
|
452 | lineno=options.lineno): | |
453 | ret = 1 |
|
453 | ret = 1 | |
454 | sys.exit(ret) |
|
454 | sys.exit(ret) |
General Comments 0
You need to be logged in to leave comments.
Login now