upstream/mercurial-mirror Commit - r26348:b80b2ee7

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

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

10

"""style and portability checker for Mercurial

10

"""style and portability checker for Mercurial

11

12

when a rule triggers wrong, do one of the following (prefer one from top):

12

when a rule triggers wrong, do one of the following (prefer one from top):

13

* do the work-around the rule suggests

13

* do the work-around the rule suggests

14

* doublecheck that it is a false match

14

* doublecheck that it is a false match

15

* improve the rule pattern

15

* improve the rule pattern

16

* add an ignore pattern to the rule (3rd arg) which matches your good line

16

* add an ignore pattern to the rule (3rd arg) which matches your good line

17

(you can append a short comment and match this, like: #re-raises, # no-py24)

17

(you can append a short comment and match this, like: #re-raises, # no-py24)

18

* change the pattern to a warning and list the exception in test-check-code-hg

18

* change the pattern to a warning and list the exception in test-check-code-hg

19

* ONLY use no--check-code for skipping entire files from external sources

19

* ONLY use no--check-code for skipping entire files from external sources

20

"""

20

"""

21

22

import re, glob, os, sys

22

import re, glob, os, sys

23

import keyword

23

import keyword

24

import optparse

24

import optparse

25

try:

25

try:

26

import re2

26

import re2

27

except ImportError:

27

except ImportError:

28

re2 = None

28

re2 = None

29

30

def compilere(pat, multiline=False):

30

def compilere(pat, multiline=False):

31

if multiline:

31

if multiline:

32

pat = '(?m)' + pat

32

pat = '(?m)' + pat

33

if re2:

33

if re2:

34

try:

34

try:

35

return re2.compile(pat)

35

return re2.compile(pat)

36

except re2.error:

36

except re2.error:

37

pass

37

pass

38

return re.compile(pat)

38

return re.compile(pat)

39

40

def repquote(m):

40

def repquote(m):

41

fromc = '.:'

41

fromc = '.:'

42

tochr = 'pq'

42

tochr = 'pq'

43

def encodechr(i):

43

def encodechr(i):

44

if i > 255:

44

if i > 255:

45

return 'u'

45

return 'u'

46

c = chr(i)

46

c = chr(i)

47

if c in ' \n':

47

if c in ' \n':

48

return c

48

return c

49

if c.isalpha():

49

if c.isalpha():

50

return 'x'

50

return 'x'

51

if c.isdigit():

51

if c.isdigit():

52

return 'n'

52

return 'n'

53

try:

53

try:

54

return tochr[fromc.find(c)]

54

return tochr[fromc.find(c)]

55

except (ValueError, IndexError):

55

except (ValueError, IndexError):

56

return 'o'

56

return 'o'

57

t = m.group('text')

57

t = m.group('text')

58

tt = ''.join(encodechr(i) for i in xrange(256))

58

tt = ''.join(encodechr(i) for i in xrange(256))

59

t = t.translate(tt)

59

t = t.translate(tt)

60

return m.group('quote') + t + m.group('quote')

60

return m.group('quote') + t + m.group('quote')

61

62

def reppython(m):

62

def reppython(m):

63

comment = m.group('comment')

63

comment = m.group('comment')

64

if comment:

64

if comment:

65

l = len(comment.rstrip())

65

l = len(comment.rstrip())

66

return "#" * l + comment[l:]

66

return "#" * l + comment[l:]

67

return repquote(m)

67

return repquote(m)

68

69

def repcomment(m):

69

def repcomment(m):

70

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

70

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

71

72

def repccomment(m):

72

def repccomment(m):

73

t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))

73

t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))

74

return m.group(1) + t + "*/"

74

return m.group(1) + t + "*/"

75

76

def repcallspaces(m):

76

def repcallspaces(m):

77

t = re.sub(r"\n\s+", "\n", m.group(2))

77

t = re.sub(r"\n\s+", "\n", m.group(2))

78

return m.group(1) + t

78

return m.group(1) + t

79

80

def repinclude(m):

80

def repinclude(m):

81

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

81

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

82

83

def rephere(m):

83

def rephere(m):

84

t = re.sub(r"\S", "x", m.group(2))

84

t = re.sub(r"\S", "x", m.group(2))

85

return m.group(1) + t

85

return m.group(1) + t

86

87

88

testpats = [

88

testpats = [

89

[

89

[

90

(r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),

90

(r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),

91

(r'\W\$?$\([^$\n]*\)\)', "don't use (()) or $(()), use 'expr'"),

91

(r'\W\$?$\([^$\n]*\)\)', "don't use (()) or $(()), use 'expr'"),

92

(r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),

92

(r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),

93

(r'(?<!hg )grep.*-a', "don't use 'grep -a', use in-line python"),

93

(r'(?<!hg )grep.*-a', "don't use 'grep -a', use in-line python"),

94

(r'sed.*-i', "don't use 'sed -i', use a temporary file"),

94

(r'sed.*-i', "don't use 'sed -i', use a temporary file"),

95

(r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),

95

(r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),

96

(r'echo -n', "don't use 'echo -n', use printf"),

96

(r'echo -n', "don't use 'echo -n', use printf"),

97

(r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*$re$)', "filter wc output"),

97

(r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*$re$)', "filter wc output"),

98

(r'head -c', "don't use 'head -c', use 'dd'"),

98

(r'head -c', "don't use 'head -c', use 'dd'"),

99

(r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),

99

(r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),

100

(r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),

100

(r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),

101

(r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),

101

(r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),

102

(r'printf.*[^\\]\\([1-9]|0\d)', "don't use 'printf \NNN', use Python"),

102

(r'printf.*[^\\]\\([1-9]|0\d)', "don't use 'printf \NNN', use Python"),

103

(r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),

103

(r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),

104

(r'\$$.*$', "don't use $(expr), use `expr`"),

104

(r'\$$.*$', "don't use $(expr), use `expr`"),

105

(r'rm -rf \*', "don't use naked rm -rf, target a directory"),

105

(r'rm -rf \*', "don't use naked rm -rf, target a directory"),

106

(r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',

106

(r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',

107

"use egrep for extended grep syntax"),

107

"use egrep for extended grep syntax"),

108

(r'/bin/', "don't use explicit paths for tools"),

108

(r'/bin/', "don't use explicit paths for tools"),

109

(r'[^\n]\Z', "no trailing newline"),

109

(r'[^\n]\Z', "no trailing newline"),

110

(r'export.*=', "don't export and assign at once"),

110

(r'export.*=', "don't export and assign at once"),

111

(r'^source\b', "don't use 'source', use '.'"),

111

(r'^source\b', "don't use 'source', use '.'"),

112

(r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),

112

(r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),

113

(r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),

113

(r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),

114

(r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),

114

(r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),

115

(r'^stop', "don't use 'stop' as a shell function name"),

115

(r'^stop', "don't use 'stop' as a shell function name"),

116

(r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),

116

(r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),

117

(r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),

117

(r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),

118

(r'^alias\b.*=', "don't use alias, use a function"),

118

(r'^alias\b.*=', "don't use alias, use a function"),

119

(r'if\s*!', "don't use '!' to negate exit status"),

119

(r'if\s*!', "don't use '!' to negate exit status"),

120

(r'/dev/u?random', "don't use entropy, use /dev/zero"),

120

(r'/dev/u?random', "don't use entropy, use /dev/zero"),

121

(r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),

121

(r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),

122

(r'^( *)\t', "don't use tabs to indent"),

122

(r'^( *)\t', "don't use tabs to indent"),

123

(r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',

123

(r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',

124

"put a backslash-escaped newline after sed 'i' command"),

124

"put a backslash-escaped newline after sed 'i' command"),

125

(r'^diff *-\w*u.*$\n(^ \$ |^$)', "prefix diff -u with cmp"),

125

(r'^diff *-\w*u.*$\n(^ \$ |^$)', "prefix diff -u with cmp"),

126

(r'seq ', "don't use 'seq', use $TESTDIR/seq.py")

126

(r'seq ', "don't use 'seq', use $TESTDIR/seq.py")

127

],

127

],

128

# warnings

128

# warnings

129

[

129

[

130

(r'^function', "don't use 'function', use old style"),

130

(r'^function', "don't use 'function', use old style"),

131

(r'^diff.*-\w*N', "don't use 'diff -N'"),

131

(r'^diff.*-\w*N', "don't use 'diff -N'"),

132

(r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),

132

(r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),

133

(r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),

133

(r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),

134

(r'kill (`|\$\()', "don't use kill, use killdaemons.py")

134

(r'kill (`|\$\()', "don't use kill, use killdaemons.py")

135

]

135

]

136

]

136

]

137

138

testfilters = [

138

testfilters = [

139

(r"( *)(#([^\n]*\S)?)", repcomment),

139

(r"( *)(#([^\n]*\S)?)", repcomment),

140

(r"<<(\S+)((.|\n)*?\n\1)", rephere),

140

(r"<<(\S+)((.|\n)*?\n\1)", rephere),

141

]

141

]

142

143

winglobmsg = "use (glob) to match Windows paths too"

143

winglobmsg = "use (glob) to match Windows paths too"

144

uprefix = r"^ \$ "

144

uprefix = r"^ \$ "

145

utestpats = [

145

utestpats = [

146

[

146

[

147

(r'^(\S.*|| [$>] .*)[ \t]\n', "trailing whitespace on non-output"),

147

(r'^(\S.*|| [$>] .*)[ \t]\n', "trailing whitespace on non-output"),

148

(uprefix + r'.*\|\s*sed[^|>\n]*\n',

148

(uprefix + r'.*\|\s*sed[^|>\n]*\n',

149

"use regex test output patterns instead of sed"),

149

"use regex test output patterns instead of sed"),

150

(uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),

150

(uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),

151

(uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),

151

(uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),

152

(uprefix + r'.*\|\| echo.*(fail|error)',

152

(uprefix + r'.*\|\| echo.*(fail|error)',

153

"explicit exit code checks unnecessary"),

153

"explicit exit code checks unnecessary"),

154

(uprefix + r'set -e', "don't use set -e"),

154

(uprefix + r'set -e', "don't use set -e"),

155

(uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),

155

(uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),

156

(uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "

156

(uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "

157

"as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx

157

"as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx

158

'# no-msys'), # in test-pull.t which is skipped on windows

158

'# no-msys'), # in test-pull.t which is skipped on windows

159

(r'^ saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),

159

(r'^ saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),

160

(r'^ changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',

160

(r'^ changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',

161

winglobmsg),

161

winglobmsg),

162

(r'^ pulling from \$TESTTMP/.*[^)]$', winglobmsg,

162

(r'^ pulling from \$TESTTMP/.*[^)]$', winglobmsg,

163

'\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows

163

'\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows

164

(r'^ reverting (?!subrepo ).*/.*[^)]$', winglobmsg),

164

(r'^ reverting (?!subrepo ).*/.*[^)]$', winglobmsg),

165

(r'^ cloning subrepo \S+/.*[^)]$', winglobmsg),

165

(r'^ cloning subrepo \S+/.*[^)]$', winglobmsg),

166

(r'^ pushing to \$TESTTMP/.*[^)]$', winglobmsg),

166

(r'^ pushing to \$TESTTMP/.*[^)]$', winglobmsg),

167

(r'^ pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),

167

(r'^ pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),

168

(r'^ moving \S+/.*[^)]$', winglobmsg),

168

(r'^ moving \S+/.*[^)]$', winglobmsg),

169

(r'^ no changes made to subrepo since.*/.*[^)]$', winglobmsg),

169

(r'^ no changes made to subrepo since.*/.*[^)]$', winglobmsg),

170

(r'^ .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),

170

(r'^ .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),

171

(r'^ .*file://\$TESTTMP',

171

(r'^ .*file://\$TESTTMP',

172

'write "file:/*/$TESTTMP" + (glob) to match on windows too'),

172

'write "file:/*/$TESTTMP" + (glob) to match on windows too'),

173

(r'^ (cat|find): .*: No such file or directory',

173

(r'^ (cat|find): .*: No such file or directory',

174

'use test -f to test for file existence'),

174

'use test -f to test for file existence'),

175

],

175

],

176

# warnings

176

# warnings

177

[

177

[

178

(r'^ [^*?/\n]* $glob$$',

178

(r'^ [^*?/\n]* $glob$$',

179

"glob match with no glob character (?*/)"),

179

"glob match with no glob character (?*/)"),

180

]

180

]

181

]

181

]

182

183

for i in [0, 1]:

183

for i in [0, 1]:

184

for tp in testpats[i]:

184

for tp in testpats[i]:

185

p = tp[0]

185

p = tp[0]

186

m = tp[1]

186

m = tp[1]

187

if p.startswith(r'^'):

187

if p.startswith(r'^'):

188

p = r"^ [$>] (%s)" % p[1:]

188

p = r"^ [$>] (%s)" % p[1:]

189

else:

189

else:

190

p = r"^ [$>] .*(%s)" % p

190

p = r"^ [$>] .*(%s)" % p

191

utestpats[i].append((p, m) + tp[2:])

191

utestpats[i].append((p, m) + tp[2:])

192

193

utestfilters = [

193

utestfilters = [

194

(r"<<(\S+)((.|\n)*?\n > \1)", rephere),

194

(r"<<(\S+)((.|\n)*?\n > \1)", rephere),

195

(r"( *)(#([^\n]*\S)?)", repcomment),

195

(r"( *)(#([^\n]*\S)?)", repcomment),

196

]

196

]

197

198

pypats = [

198

pypats = [

199

[

199

[

200

(r'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),

200

(r'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),

201

(r'^\s*def\s*\w+\s*\(.*,\s*\(',

201

(r'^\s*def\s*\w+\s*\(.*,\s*\(',

202

"tuple parameter unpacking not available in Python 3+"),

202

"tuple parameter unpacking not available in Python 3+"),

203

(r'lambda\s*$.*,.*$',

203

(r'lambda\s*$.*,.*$',

204

"tuple parameter unpacking not available in Python 3+"),

204

"tuple parameter unpacking not available in Python 3+"),

205

(r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',

205

(r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',

206

'2to3 can\'t always rewrite "import qux, foo.bar", '

206

'2to3 can\'t always rewrite "import qux, foo.bar", '

207

'use "import foo.bar" on its own line instead.'),

207

'use "import foo.bar" on its own line instead.'),

208

(r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),

208

(r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),

209

(r'\breduce\s*\(.*', "reduce is not available in Python 3+"),

209

(r'\breduce\s*\(.*', "reduce is not available in Python 3+"),

210

(r'dict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',

210

(r'dict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',

211

'dict-from-generator'),

211

'dict-from-generator'),

212

(r'\.has_key\b', "dict.has_key is not available in Python 3+"),

212

(r'\.has_key\b', "dict.has_key is not available in Python 3+"),

213

(r'\s<>\s', '<> operator is not available in Python 3+, use !='),

213

(r'\s<>\s', '<> operator is not available in Python 3+, use !='),

214

(r'^\s*\t', "don't use tabs"),

214

(r'^\s*\t', "don't use tabs"),

215

(r'\S;\s*\n', "semicolon"),

215

(r'\S;\s*\n', "semicolon"),

216

(r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),

216

(r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),

217

(r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),

217

(r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),

218

(r'(\w|\)),\w', "missing whitespace after ,"),

218

(r'(\w|\)),\w', "missing whitespace after ,"),

219

(r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),

219

(r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),

220

(r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),

220

(r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),

221

(r'.{81}', "line too long"),

221

(r'.{81}', "line too long"),

222

(r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),

222

(r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),

223

(r'[^\n]\Z', "no trailing newline"),

223

(r'[^\n]\Z', "no trailing newline"),

224

(r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),

224

(r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),

225

# (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',

225

# (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',

226

# "don't use underbars in identifiers"),

226

# "don't use underbars in identifiers"),

227

(r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',

227

(r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',

228

"don't use camelcase in identifiers"),

228

"don't use camelcase in identifiers"),

229

229

230

"linebreak after :"),

230

"linebreak after :"),

231

(r'class\s[^( \n]+:', "old-style class, use class foo(object)"),

231

(r'class\s[^( \n]+:', "old-style class, use class foo(object)"),

232

(r'class\s[^( \n]+:',

232

(r'class\s[^( \n]+:',

233

"class foo() creates old style object, use class foo(object)"),

233

"class foo() creates old style object, use class foo(object)"),

234

(r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist

234

(r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist

235

if k not in ('print', 'exec')),

235

if k not in ('print', 'exec')),

236

"Python keyword is not a function"),

236

"Python keyword is not a function"),

237

(r',]', "unneeded trailing ',' in list"),

237

(r',]', "unneeded trailing ',' in list"),

238

# (r'class\s[A-Z][^\(]*\((?!Exception)',

238

# (r'class\s[A-Z][^\(]*\((?!Exception)',

239

# "don't capitalize non-exception classes"),

239

# "don't capitalize non-exception classes"),

240

# (r'in range\(', "use xrange"),

240

# (r'in range\(', "use xrange"),

241

# (r'^\s*print\s+', "avoid using print in core and extensions"),

241

# (r'^\s*print\s+', "avoid using print in core and extensions"),

242

(r'[\x80-\xff]', "non-ASCII character literal"),

242

(r'[\x80-\xff]', "non-ASCII character literal"),

243

(r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),

243

(r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),

244

(r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),

244

(r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),

245

"gratuitous whitespace after Python keyword"),

245

"gratuitous whitespace after Python keyword"),

246

(r'([$\[][ \t]\S)|(\S[ \t][$\]])', "gratuitous whitespace in () or []"),

246

(r'([$\[][ \t]\S)|(\S[ \t][$\]])', "gratuitous whitespace in () or []"),

247

# (r'\s\s=', "gratuitous whitespace before ="),

247

# (r'\s\s=', "gratuitous whitespace before ="),

248

(r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',

248

(r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',

249

"missing whitespace around operator"),

249

"missing whitespace around operator"),

250

(r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',

250

(r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',

251

"missing whitespace around operator"),

251

"missing whitespace around operator"),

252

(r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',

252

(r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',

253

"missing whitespace around operator"),

253

"missing whitespace around operator"),

254

(r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',

254

(r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',

255

"wrong whitespace around ="),

255

"wrong whitespace around ="),

256

(r'\([^()]*( =[^=]|[^<>!=]= )',

256

(r'\([^()]*( =[^=]|[^<>!=]= )',

257

"no whitespace around = for named parameters"),

257

"no whitespace around = for named parameters"),

258

(r'raise Exception', "don't raise generic exceptions"),

258

(r'raise Exception', "don't raise generic exceptions"),

259

(r'raise [^,(]+, ($[^$]+\)|[^,]+)$',

259

(r'raise [^,(]+, ($[^$]+\)|[^,]+)$',

260

"don't use old-style two-argument raise, use Exception(message)"),

260

"don't use old-style two-argument raise, use Exception(message)"),

261

(r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),

261

(r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),

262

(r' [=!]=\s+(True|False|None)',

262

(r' [=!]=\s+(True|False|None)',

263

"comparison with singleton, use 'is' or 'is not' instead"),

263

"comparison with singleton, use 'is' or 'is not' instead"),

264

(r'^\s*(while|if) [01]:',

264

(r'^\s*(while|if) [01]:',

265

"use True/False for constant Boolean expression"),

265

"use True/False for constant Boolean expression"),

266

(r'(?:(?<!def)\s+|\()hasattr',

266

(r'(?:(?<!def)\s+|\()hasattr',

267

'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),

267

'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),

268

(r'opener$[^)]*$.read\(',

268

(r'opener$[^)]*$.read\(',

269

"use opener.read() instead"),

269

"use opener.read() instead"),

270

(r'opener$[^)]*$.write\(',

270

(r'opener$[^)]*$.write\(',

271

"use opener.write() instead"),

271

"use opener.write() instead"),

272

(r'[\s$](open|file)\([^)]*$\.read\(',

272

(r'[\s$](open|file)\([^)]*$\.read\(',

273

"use util.readfile() instead"),

273

"use util.readfile() instead"),

274

(r'[\s$](open|file)\([^)]*$\.write\(',

274

(r'[\s$](open|file)\([^)]*$\.write\(',

275

"use util.writefile() instead"),

275

"use util.writefile() instead"),

276

(r'^[\s$]*(open(er)?|file)\([^)]*$',

276

(r'^[\s$]*(open(er)?|file)\([^)]*$',

277

"always assign an opened file to a variable, and close it afterwards"),

277

"always assign an opened file to a variable, and close it afterwards"),

278

(r'[\s$](open|file)\([^)]*$\.',

278

(r'[\s$](open|file)\([^)]*$\.',

279

"always assign an opened file to a variable, and close it afterwards"),

279

"always assign an opened file to a variable, and close it afterwards"),

280

(r'(?i)descend[e]nt', "the proper spelling is descendAnt"),

280

(r'(?i)descend[e]nt', "the proper spelling is descendAnt"),

281

(r'\.debug\(\_', "don't mark debug messages for translation"),

281

(r'\.debug\(\_', "don't mark debug messages for translation"),

282

(r'\.strip\.split', "no need to strip before splitting"),

282

(r'\.strip\.split', "no need to strip before splitting"),

283

(r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),

283

(r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),

284

(r'^\s*except\s([^$,]+|\([^$]+\))\s*,',

284

(r'^\s*except\s([^$,]+|\([^$]+\))\s*,',

285

'legacy exception syntax; use "as" instead of ","'),

285

'legacy exception syntax; use "as" instead of ","'),

286

(r':\n( )*( ){1,3}[^ ]', "must indent 4 spaces"),

286

(r':\n( )*( ){1,3}[^ ]', "must indent 4 spaces"),

287

(r'ui\.(status|progress|write|note|warn)\([\'\"]x',

287

(r'ui\.(status|progress|write|note|warn)\([\'\"]x',

288

"missing _() in ui message (use () to hide false-positives)"),

288

"missing _() in ui message (use () to hide false-positives)"),

289

(r'release$.*wlock, .*lock$', "wrong lock release order"),

289

(r'release$.*wlock, .*lock$', "wrong lock release order"),

290

(r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),

290

(r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),

291

(r'os\.path\.join$.*, *(""|\'\')$',

291

(r'os\.path\.join$.*, *(""|\'\')$',

292

"use pathutil.normasprefix(path) instead of os.path.join(path, '')"),

292

"use pathutil.normasprefix(path) instead of os.path.join(path, '')"),

293

(r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),

293

(r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),

294

# XXX only catch mutable arguments on the first line of the definition

295

(r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),

294

],

296

],

295

# warnings

297

# warnings

296

[

298

[

297

(r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),

299

(r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),

298

]

300

]

299

]

301

]

300

302

301

pyfilters = [

303

pyfilters = [

302

(r"""(?msx)(?P<comment>\#.*?$)|

304

(r"""(?msx)(?P<comment>\#.*?$)|

303

((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))

305

((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))

304

(?P<text>(([^\\]|\\.)*?))

306

(?P<text>(([^\\]|\\.)*?))

305

(?P=quote))""", reppython),

307

(?P=quote))""", reppython),

306

]

308

]

307

309

308

txtfilters = []

310

txtfilters = []

309

311

310

txtpats = [

312

txtpats = [

311

[

313

[

312

('\s$', 'trailing whitespace'),

314

('\s$', 'trailing whitespace'),

313

('.. note::[ \n][^\n]', 'add two newlines after note::')

315

('.. note::[ \n][^\n]', 'add two newlines after note::')

314

],

316

],

315

[]

317

[]

316

]

318

]

317

319

318

cpats = [

320

cpats = [

319

[

321

[

320

(r'//', "don't use //-style comments"),

322

(r'//', "don't use //-style comments"),

321

(r'^ ', "don't use spaces to indent"),

323

(r'^ ', "don't use spaces to indent"),

322

(r'\S\t', "don't use tabs except for indent"),

324

(r'\S\t', "don't use tabs except for indent"),

323

(r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),

325

(r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),

324

(r'.{81}', "line too long"),

326

(r'.{81}', "line too long"),

325

(r'(while|if|do|for)\(', "use space after while/if/do/for"),

327

(r'(while|if|do|for)\(', "use space after while/if/do/for"),

326

(r'return\(', "return is not a function"),

328

(r'return\(', "return is not a function"),

327

(r' ;', "no space before ;"),

329

(r' ;', "no space before ;"),

328

(r'[^;] \)', "no space before )"),

330

(r'[^;] \)', "no space before )"),

329

(r'[)][{]', "space between ) and {"),

331

(r'[)][{]', "space between ) and {"),

330

(r'\w+\* \w+', "use int *foo, not int* foo"),

332

(r'\w+\* \w+', "use int *foo, not int* foo"),

331

(r'\W$[^$]+\) \w+', "use (int)foo, not (int) foo"),

333

(r'\W$[^$]+\) \w+', "use (int)foo, not (int) foo"),

332

(r'\w+ (\+\+|--)', "use foo++, not foo ++"),

334

(r'\w+ (\+\+|--)', "use foo++, not foo ++"),

333

(r'\w,\w', "missing whitespace after ,"),

335

(r'\w,\w', "missing whitespace after ,"),

334

(r'^[^#]\w[+/*]\w', "missing whitespace in expression"),

336

(r'^[^#]\w[+/*]\w', "missing whitespace in expression"),

335

(r'^#\s+\w', "use #foo, not # foo"),

337

(r'^#\s+\w', "use #foo, not # foo"),

336

(r'[^\n]\Z', "no trailing newline"),

338

(r'[^\n]\Z', "no trailing newline"),

337

(r'^\s*#import\b', "use only #include in standard C code"),

339

(r'^\s*#import\b', "use only #include in standard C code"),

338

],

340

],

339

# warnings

341

# warnings

340

[]

342

[]

341

]

343

]

342

344

343

cfilters = [

345

cfilters = [

344

(r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),

346

(r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),

345

(r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),

347

(r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),

346

(r'''(#\s*include\s+<)([^>]+)>''', repinclude),

348

(r'''(#\s*include\s+<)([^>]+)>''', repinclude),

347

(r'($)([^)]+$)', repcallspaces),

349

(r'($)([^)]+$)', repcallspaces),

348

]

350

]

349

351

350

inutilpats = [

352

inutilpats = [

351

[

353

[

352

(r'\bui\.', "don't use ui in util"),

354

(r'\bui\.', "don't use ui in util"),

353

],

355

],

354

# warnings

356

# warnings

355

[]

357

[]

356

]

358

]

357

359

358

inrevlogpats = [

360

inrevlogpats = [

359

[

361

[

360

(r'\brepo\.', "don't use repo in revlog"),

362

(r'\brepo\.', "don't use repo in revlog"),

361

],

363

],

362

# warnings

364

# warnings

363

[]

365

[]

364

]

366

]

365

367

366

webtemplatefilters = []

368

webtemplatefilters = []

367

369

368

webtemplatepats = [

370

webtemplatepats = [

369

[],

371

[],

370

[

372

[

371

(r'{desc(\|(?!websub|firstline)[^\|]*)+}',

373

(r'{desc(\|(?!websub|firstline)[^\|]*)+}',

372

'follow desc keyword with either firstline or websub'),

374

'follow desc keyword with either firstline or websub'),

373

]

375

]

374

]

376

]

375

377

376

checks = [

378

checks = [

377

('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),

379

('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),

378

('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),

380

('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),

379

('c', r'.*\.[ch]$', '', cfilters, cpats),

381

('c', r'.*\.[ch]$', '', cfilters, cpats),

380

('unified test', r'.*\.t$', '', utestfilters, utestpats),

382

('unified test', r'.*\.t$', '', utestfilters, utestpats),

381

('layering violation repo in revlog', r'mercurial/revlog\.py', '',

383

('layering violation repo in revlog', r'mercurial/revlog\.py', '',

382

pyfilters, inrevlogpats),

384

pyfilters, inrevlogpats),

383

('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,

385

('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,

384

inutilpats),

386

inutilpats),

385

('txt', r'.*\.txt$', '', txtfilters, txtpats),

387

('txt', r'.*\.txt$', '', txtfilters, txtpats),

386

('web template', r'mercurial/templates/.*\.tmpl', '',

388

('web template', r'mercurial/templates/.*\.tmpl', '',

387

webtemplatefilters, webtemplatepats),

389

webtemplatefilters, webtemplatepats),

388

]

390

]

389

391

390

def _preparepats():

392

def _preparepats():

391

for c in checks:

393

for c in checks:

392

failandwarn = c[-1]

394

failandwarn = c[-1]

393

for pats in failandwarn:

395

for pats in failandwarn:

394

for i, pseq in enumerate(pats):

396

for i, pseq in enumerate(pats):

395

# fix-up regexes for multi-line searches

397

# fix-up regexes for multi-line searches

396

p = pseq[0]

398

p = pseq[0]

397

# \s doesn't match \n

399

# \s doesn't match \n

398

p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)

400

p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)

399

# [^...] doesn't match newline

401

# [^...] doesn't match newline

400

p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)

402

p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)

401

403

402

pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]

404

pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]

403

filters = c[3]

405

filters = c[3]

404

for i, flt in enumerate(filters):

406

for i, flt in enumerate(filters):

405

filters[i] = re.compile(flt[0]), flt[1]

407

filters[i] = re.compile(flt[0]), flt[1]

406

_preparepats()

408

_preparepats()

407

409

408

class norepeatlogger(object):

410

class norepeatlogger(object):

409

def __init__(self):

411

def __init__(self):

410

self._lastseen = None

412

self._lastseen = None

411

413

412

def log(self, fname, lineno, line, msg, blame):

414

def log(self, fname, lineno, line, msg, blame):

413

"""print error related a to given line of a given file.

415

"""print error related a to given line of a given file.

414

416

415

The faulty line will also be printed but only once in the case

417

The faulty line will also be printed but only once in the case

416

of multiple errors.

418

of multiple errors.

417

419

418

:fname: filename

420

:fname: filename

419

:lineno: line number

421

:lineno: line number

420

:line: actual content of the line

422

:line: actual content of the line

421

:msg: error message

423

:msg: error message

422

"""

424

"""

423

msgid = fname, lineno, line

425

msgid = fname, lineno, line

424

if msgid != self._lastseen:

426

if msgid != self._lastseen:

425

if blame:

427

if blame:

426

print "%s:%d (%s):" % (fname, lineno, blame)

428

print "%s:%d (%s):" % (fname, lineno, blame)

427

else:

429

else:

428

print "%s:%d:" % (fname, lineno)

430

print "%s:%d:" % (fname, lineno)

429

print " > %s" % line

431

print " > %s" % line

430

self._lastseen = msgid

432

self._lastseen = msgid

431

print " " + msg

433

print " " + msg

432

434

433

_defaultlogger = norepeatlogger()

435

_defaultlogger = norepeatlogger()

434

436

435

def getblame(f):

437

def getblame(f):

436

lines = []

438

lines = []

437

for l in os.popen('hg annotate -un %s' % f):

439

for l in os.popen('hg annotate -un %s' % f):

438

start, line = l.split(':', 1)

440

start, line = l.split(':', 1)

439

user, rev = start.split()

441

user, rev = start.split()

440

lines.append((line[1:-1], user, rev))

442

lines.append((line[1:-1], user, rev))

441

return lines

443

return lines

442

444

443

def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,

445

def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,

444

blame=False, debug=False, lineno=True):

446

blame=False, debug=False, lineno=True):

445

"""checks style and portability of a given file

447

"""checks style and portability of a given file

446

448

447

:f: filepath

449

:f: filepath

448

:logfunc: function used to report error

450

:logfunc: function used to report error

449

logfunc(filename, linenumber, linecontent, errormessage)

451

logfunc(filename, linenumber, linecontent, errormessage)

450

:maxerr: number of error to display before aborting.

452

:maxerr: number of error to display before aborting.

451

Set to false (default) to report all errors

453

Set to false (default) to report all errors

452

454

453

return True if no error is found, False otherwise.

455

return True if no error is found, False otherwise.

454

"""

456

"""

455

blamecache = None

457

blamecache = None

456

result = True

458

result = True

457

459

458

try:

460

try:

459

fp = open(f)

461

fp = open(f)

460

except IOError as e:

462

except IOError as e:

461

print "Skipping %s, %s" % (f, str(e).split(':', 1)[0])

463

print "Skipping %s, %s" % (f, str(e).split(':', 1)[0])

462

return result

464

return result

463

pre = post = fp.read()

465

pre = post = fp.read()

464

fp.close()

466

fp.close()

465

467

466

for name, match, magic, filters, pats in checks:

468

for name, match, magic, filters, pats in checks:

467

if debug:

469

if debug:

468

print name, f

470

print name, f

469

fc = 0

471

fc = 0

470

if not (re.match(match, f) or (magic and re.search(magic, f))):

472

if not (re.match(match, f) or (magic and re.search(magic, f))):

471

if debug:

473

if debug:

472

print "Skipping %s for %s it doesn't match %s" % (

474

print "Skipping %s for %s it doesn't match %s" % (

473

name, match, f)

475

name, match, f)

474

continue

476

continue

475

if "no-" "check-code" in pre:

477

if "no-" "check-code" in pre:

476

print "Skipping %s it has no-" "check-code" % f

478

print "Skipping %s it has no-" "check-code" % f

477

return "Skip" # skip checking this file

479

return "Skip" # skip checking this file

478

for p, r in filters:

480

for p, r in filters:

479

post = re.sub(p, r, post)

481

post = re.sub(p, r, post)

480

nerrs = len(pats[0]) # nerr elements are errors

482

nerrs = len(pats[0]) # nerr elements are errors

481

if warnings:

483

if warnings:

482

pats = pats[0] + pats[1]

484

pats = pats[0] + pats[1]

483

else:

485

else:

484

pats = pats[0]

486

pats = pats[0]

485

# print post # uncomment to show filtered version

487

# print post # uncomment to show filtered version

486

488

487

if debug:

489

if debug:

488

print "Checking %s for %s" % (name, f)

490

print "Checking %s for %s" % (name, f)

489

491

490

prelines = None

492

prelines = None

491

errors = []

493

errors = []

492

for i, pat in enumerate(pats):

494

for i, pat in enumerate(pats):

493

if len(pat) == 3:

495

if len(pat) == 3:

494

p, msg, ignore = pat

496

p, msg, ignore = pat

495

else:

497

else:

496

p, msg = pat

498

p, msg = pat

497

ignore = None

499

ignore = None

498

if i >= nerrs:

500

if i >= nerrs:

499

msg = "warning: " + msg

501

msg = "warning: " + msg

500

502

501

pos = 0

503

pos = 0

502

n = 0

504

n = 0

503

for m in p.finditer(post):

505

for m in p.finditer(post):

504

if prelines is None:

506

if prelines is None:

505

prelines = pre.splitlines()

507

prelines = pre.splitlines()

506

postlines = post.splitlines(True)

508

postlines = post.splitlines(True)

507

509

508

start = m.start()

510

start = m.start()

509

while n < len(postlines):

511

while n < len(postlines):

510

step = len(postlines[n])

512

step = len(postlines[n])

511

if pos + step > start:

513

if pos + step > start:

512

break

514

break

513

pos += step

515

pos += step

514

n += 1

516

n += 1

515

l = prelines[n]

517

l = prelines[n]

516

518

517

if ignore and re.search(ignore, l, re.MULTILINE):

519

if ignore and re.search(ignore, l, re.MULTILINE):

518

if debug:

520

if debug:

519

print "Skipping %s for %s:%s (ignore pattern)" % (

521

print "Skipping %s for %s:%s (ignore pattern)" % (

520

name, f, n)

522

name, f, n)

521

continue

523

continue

522

bd = ""

524

bd = ""

523

if blame:

525

if blame:

524

bd = 'working directory'

526

bd = 'working directory'

525

if not blamecache:

527

if not blamecache:

526

blamecache = getblame(f)

528

blamecache = getblame(f)

527

if n < len(blamecache):

529

if n < len(blamecache):

528

bl, bu, br = blamecache[n]

530

bl, bu, br = blamecache[n]

529

if bl == l:

531

if bl == l:

530

bd = '%s@%s' % (bu, br)

532

bd = '%s@%s' % (bu, br)

531

533

532

errors.append((f, lineno and n + 1, l, msg, bd))

534

errors.append((f, lineno and n + 1, l, msg, bd))

533

result = False

535

result = False

534

536

535

errors.sort()

537

errors.sort()

536

for e in errors:

538

for e in errors:

537

logfunc(*e)

539

logfunc(*e)

538

fc += 1

540

fc += 1

539

if maxerr and fc >= maxerr:

541

if maxerr and fc >= maxerr:

540

print " (too many errors, giving up)"

542

print " (too many errors, giving up)"

541

break

543

break

542

544

543

return result

545

return result

544

546

545

if __name__ == "__main__":

547

if __name__ == "__main__":

546

parser = optparse.OptionParser("%prog [options] [files]")

548

parser = optparse.OptionParser("%prog [options] [files]")

547

parser.add_option("-w", "--warnings", action="store_true",

549

parser.add_option("-w", "--warnings", action="store_true",

548

help="include warning-level checks")

550

help="include warning-level checks")

549

parser.add_option("-p", "--per-file", type="int",

551

parser.add_option("-p", "--per-file", type="int",

550

help="max warnings per file")

552

help="max warnings per file")

551

parser.add_option("-b", "--blame", action="store_true",

553

parser.add_option("-b", "--blame", action="store_true",

552

help="use annotate to generate blame info")

554

help="use annotate to generate blame info")

553

parser.add_option("", "--debug", action="store_true",

555

parser.add_option("", "--debug", action="store_true",

554

help="show debug information")

556

help="show debug information")

555

parser.add_option("", "--nolineno", action="store_false",

557

parser.add_option("", "--nolineno", action="store_false",

556

dest='lineno', help="don't show line numbers")

558

dest='lineno', help="don't show line numbers")

557

559

558

parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,

560

parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,

559

lineno=True)

561

lineno=True)

560

(options, args) = parser.parse_args()

562

(options, args) = parser.parse_args()

561

563

562

if len(args) == 0:

564

if len(args) == 0:

563

check = glob.glob("*")

565

check = glob.glob("*")

564

else:

566

else:

565

check = args

567

check = args

566

568

567

ret = 0

569

ret = 0

568

for f in check:

570

for f in check:

569

if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,

571

if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,

570

blame=options.blame, debug=options.debug,

572

blame=options.blame, debug=options.debug,

571

lineno=options.lineno):

573

lineno=options.lineno):

572

ret = 1

574

ret = 1

573

sys.exit(ret)

575

sys.exit(ret)

	Site-wide shortcuts
/	Use quick search box
g h	Goto home page
g g	Goto my private gists page
g G	Goto my public gists page
g 0-9	Goto bookmarked items from 0-9
n r	New repository page
n g	New gist page

	Repositories
g s	Goto summary page
g c	Goto changelog page
g f	Goto files page
g F	Goto files page with file search activated
g p	Goto pull requests page
g o	Goto repository settings
g O	Goto repository access permissions settings
t s	Toggle sidebar on some pages

             #!/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.
             """style and portability checker for Mercurial
             when a rule triggers wrong, do one of the following (prefer one from top):
              * do the work-around the rule suggests
              * doublecheck that it is a false match
              * improve the rule pattern
              * add an ignore pattern to the rule (3rd arg) which matches your good line
                (you can append a short comment and match this, like: #re-raises, # no-py24)
              * change the pattern to a warning and list the exception in test-check-code-hg
              * ONLY use no--check-code for skipping entire files from external sources
             """
             import re, glob, os, sys
             import keyword
             import optparse
             try:
                 import re2
             except ImportError:
                 re2 = None
             def compilere(pat, multiline=False):
                 if multiline:
                     pat = '(?m)' + pat
                 if re2:
                     try:
                         return re2.compile(pat)
                     except re2.error:
                         pass
                 return re.compile(pat)
             def repquote(m):
                 fromc = '.:'
                 tochr = 'pq'
                 def encodechr(i):
                     if i > 255:
                         return 'u'
                     c = chr(i)
                     if c in ' \n':
                         return c
                     if c.isalpha():
                         return 'x'
                     if c.isdigit():
                         return 'n'
                     try:
                         return tochr[fromc.find(c)]
                     except (ValueError, IndexError):
                         return 'o'
                 t = m.group('text')
                 tt = ''.join(encodechr(i) for i in xrange(256))
                 t = t.translate(tt)
                 return m.group('quote') + t + m.group('quote')
             def reppython(m):
                 comment = m.group('comment')
                 if comment:
                     l = len(comment.rstrip())
                     return "#" * l + comment[l:]
                 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\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
                 (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
                 (r'(?<!hg )grep.*-a', "don't use 'grep -a', use in-line python"),
                 (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
                 (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
                 (r'echo -n', "don't use 'echo -n', use printf"),
                 (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
                 (r'head -c', "don't use 'head -c', use 'dd'"),
                 (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
                 (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
                 (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
                 (r'printf.*[^\\]\\([1-9]|0\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'[^\n]\Z', "no trailing newline"),
                 (r'export.*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                 (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
                 (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
                 (r'^stop\(\)', "don't use 'stop' as a shell function name"),
                 (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
                 (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
                 (r'^alias\b.*=', "don't use alias, use a function"),
                 (r'if\s*!', "don't use '!' to negate exit status"),
                 (r'/dev/u?random', "don't use entropy, use /dev/zero"),
                 (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
                 (r'^( *)\t', "don't use tabs to indent"),
                 (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
                  "put a backslash-escaped newline after sed 'i' command"),
                 (r'^diff *-\w*u.*$\n(^  \$ |^$)', "prefix diff -u with cmp"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py")
               ],
               # warnings
               [
                 (r'^function', "don't use 'function', use old style"),
                 (r'^diff.*-\w*N', "don't use 'diff -N'"),
                 (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
                 (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
                 (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
               ]
             ]
             testfilters = [
                 (r"( *)(#([^\n]*\S)?)", repcomment),
                 (r"<<(\S+)((.|\n)*?\n\1)", rephere),
             ]
             winglobmsg = "use (glob) to match Windows paths too"
             uprefix = r"^  \$ "
             utestpats = [
               [
                 (r'^(\S.*||  [$>] .*)[ \t]\n', "trailing whitespace on non-output"),
                 (uprefix + r'.*\|\s*sed[^|>\n]*\n',
                  "use regex test output patterns instead of sed"),
                 (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
                 (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
                 (uprefix + r'.*\|\| echo.*(fail|error)',
                  "explicit exit code checks unnecessary"),
                 (uprefix + r'set -e', "don't use set -e"),
                 (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
                 (uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "
                  "as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx
                  '# no-msys'), # in test-pull.t which is skipped on windows
                 (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
                 (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
                  winglobmsg),
                 (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
                  '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
                 (r'^  reverting (?!subrepo ).*/.*[^)]$', winglobmsg),
                 (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
                 (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
                 (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
                 (r'^  moving \S+/.*[^)]$', winglobmsg),
                 (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
                 (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
                 (r'^  .*file://\$TESTTMP',
                  'write "file:/*/$TESTTMP" + (glob) to match on windows too'),
                 (r'^  (cat|find): .*: No such file or directory',
                  'use test -f to test for file existence'),
               ],
               # warnings
               [
                 (r'^  [^*?/\n]* \(glob\)$',
                  "glob match with no glob character (?*/)"),
               ]
             ]
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%s)" % p[1:]
                     else:
                         p = r"^  [$>] .*(%s)" % p
                     utestpats[i].append((p, m) + tp[2:])
             utestfilters = [
                 (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
                 (r"( *)(#([^\n]*\S)?)", repcomment),
             ]
             pypats = [
               [
                 (r'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),
                 (r'^\s*def\s*\w+\s*\(.*,\s*\(',
                  "tuple parameter unpacking not available in Python 3+"),
                 (r'lambda\s*\(.*,.*\)',
                  "tuple parameter unpacking not available in Python 3+"),
                 (r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',
                  '2to3 can\'t always rewrite "import qux, foo.bar", '
                  'use "import foo.bar" on its own line instead.'),
                 (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
                 (r'\breduce\s*\(.*', "reduce is not available in Python 3+"),
                 (r'dict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
                  'dict-from-generator'),
                 (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
                 (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
                 (r'^\s*\t', "don't use tabs"),
                 (r'\S;\s*\n', "semicolon"),
                 (r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
                 (r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
                 (r'(\w|\)),\w', "missing whitespace after ,"),
                 (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
                 (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
                 (r'.{81}', "line too long"),
                 (r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
             #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
             #     "don't use underbars in identifiers"),
                 (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
                  "don't use camelcase in identifiers"),
                 (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                  "linebreak after :"),
                 (r'class\s[^( \n]+:', "old-style class, use class foo(object)"),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)"),
                 (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                                         if k not in ('print', 'exec')),
                  "Python keyword is not 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() has no bytes counterpart, use %"),
                 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
                  "gratuitous whitespace after Python keyword"),
                 (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "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'\([^()]*( =[^=]|[^<>!=]= )',
                  "no whitespace around = for named parameters"),
                 (r'raise Exception', "don't raise generic exceptions"),
                 (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                  "don't use old-style two-argument raise, use Exception(message)"),
                 (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                 (r' [=!]=\s+(True|False|None)',
                  "comparison with singleton, use 'is' or 'is not' instead"),
                 (r'^\s*(while|if) [01]:',
                  "use True/False for constant Boolean expression"),
                 (r'(?:(?<!def)\s+|\()hasattr',
                  'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
                 (r'opener\([^)]*\).read\(',
                  "use opener.read() instead"),
                 (r'opener\([^)]*\).write\(',
                  "use opener.write() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.read\(',
                  "use util.readfile() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.write\(',
                  "use util.writefile() instead"),
                 (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'[\s\(](open|file)\([^)]*\)\.',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
                 (r'\.debug\(\_', "don't mark debug messages for translation"),
                 (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
                 (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
                 (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
                  'legacy exception syntax; use "as" instead of ","'),
                 (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                 (r'ui\.(status|progress|write|note|warn)\([\'\"]x',
                  "missing _() in ui message (use () to hide false-positives)"),
                 (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
                 (r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
                 (r'os\.path\.join\(.*, *(""|\'\')\)',
                  "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
                 (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
+                # XXX only catch mutable arguments on the first line of the definition
+                (r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),
               ],
               # warnings
               [
                 (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
               ]
             ]
             pyfilters = [
                 (r"""(?msx)(?P<comment>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""", reppython),
             ]
             txtfilters = []
             txtpats = [
               [
                 ('\s$', 'trailing whitespace'),
                 ('.. note::[ \n][^\n]', 'add two newlines after note::')
               ],
               []
             ]
             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[ \t]+|^[ \t]+)\n', "trailing whitespace"),
                 (r'.{81}', "line too long"),
                 (r'(while|if|do|for)\(', "use space after while/if/do/for"),
                 (r'return\(', "return is not a function"),
                 (r' ;', "no space before ;"),
                 (r'[^;] \)', "no space before )"),
                 (r'[)][{]', "space between ) and {"),
                 (r'\w+\* \w+', "use int *foo, not int* foo"),
                 (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
                 (r'\w+ (\+\+|--)', "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"),
                 (r'^\s*#import\b', "use only #include in standard C code"),
               ],
               # warnings
               []
             ]
             cfilters = [
                 (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
                 (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
                 (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
                 (r'(\()([^)]+\))', repcallspaces),
             ]
             inutilpats = [
               [
                 (r'\bui\.', "don't use ui in util"),
               ],
               # warnings
               []
             ]
             inrevlogpats = [
               [
                 (r'\brepo\.', "don't use repo in revlog"),
               ],
               # warnings
               []
             ]
             webtemplatefilters = []
             webtemplatepats = [
               [],
               [
                 (r'{desc(\|(?!websub|firstline)[^\|]*)+}',
                  'follow desc keyword with either firstline or websub'),
               ]
             ]
             checks = [
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
                 ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),
                 ('c', r'.*\.[ch]$', '', cfilters, cpats),
                 ('unified test', r'.*\.t$', '', utestfilters, utestpats),
                 ('layering violation repo in revlog', r'mercurial/revlog\.py', '',
                  pyfilters, inrevlogpats),
                 ('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,
                  inutilpats),
                 ('txt', r'.*\.txt$', '', txtfilters, txtpats),
                 ('web template', r'mercurial/templates/.*\.tmpl', '',
                  webtemplatefilters, webtemplatepats),
             ]
             def _preparepats():
                 for c in checks:
                     failandwarn = c[-1]
                     for pats in failandwarn:
                         for i, pseq in enumerate(pats):
                             # fix-up regexes for multi-line searches
                             p = pseq[0]
                             # \s doesn't match \n
                             p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
                             # [^...] doesn't match newline
                             p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)
                             pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]
                     filters = c[3]
                     for i, flt in enumerate(filters):
                         filters[i] = re.compile(flt[0]), flt[1]
             _preparepats()
             class norepeatlogger(object):
                 def __init__(self):
                     self._lastseen = None
                 def log(self, fname, lineno, line, msg, blame):
                     """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:
                         if blame:
                             print "%s:%d (%s):" % (fname, lineno, blame)
                         else:
                             print "%s:%d:" % (fname, lineno)
                         print " > %s" % line
                         self._lastseen = msgid
                     print " " + msg
             _defaultlogger = norepeatlogger()
             def getblame(f):
                 lines = []
                 for l in os.popen('hg annotate -un %s' % f):
                     start, line = l.split(':', 1)
                     user, rev = start.split()
                     lines.append((line[1:-1], user, rev))
                 return lines
             def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,
                           blame=False, debug=False, lineno=True):
                 """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 aborting.
                          Set to false (default) to report all errors
                 return True if no error is found, False otherwise.
                 """
                 blamecache = None
                 result = True
                 try:
                     fp = open(f)
                 except IOError as e:
                     print "Skipping %s, %s" % (f, str(e).split(':', 1)[0])
                     return result
                 pre = post = fp.read()
                 fp.close()
                 for name, match, magic, filters, pats in checks:
                     if debug:
                         print name, f
                     fc = 0
                     if not (re.match(match, f) or (magic and re.search(magic, f))):
                         if debug:
                             print "Skipping %s for %s it doesn't match %s" % (
                                    name, match, f)
                         continue
                     if "no-" "check-code" in pre:
                         print "Skipping %s it has no-" "check-code" % f
                         return "Skip" # skip checking this file
                     for p, r in filters:
                         post = re.sub(p, r, post)
                     nerrs = len(pats[0]) # nerr elements are errors
                     if warnings:
                         pats = pats[0] + pats[1]
                     else:
                         pats = pats[0]
                     # print post # uncomment to show filtered version
                     if debug:
                         print "Checking %s for %s" % (name, f)
                     prelines = None
                     errors = []
                     for i, pat in enumerate(pats):
                         if len(pat) == 3:
                             p, msg, ignore = pat
                         else:
                             p, msg = pat
                             ignore = None
                         if i >= nerrs:
                             msg = "warning: " + msg
                         pos = 0
                         n = 0
                         for m in p.finditer(post):
                             if prelines is None:
                                 prelines = pre.splitlines()
                                 postlines = post.splitlines(True)
                             start = m.start()
                             while n < len(postlines):
                                 step = len(postlines[n])
                                 if pos + step > start:
                                     break
                                 pos += step
                                 n += 1
                             l = prelines[n]
                             if ignore and re.search(ignore, l, re.MULTILINE):
                                 if debug:
                                     print "Skipping %s for %s:%s (ignore pattern)" % (
                                         name, f, n)
                                 continue
                             bd = ""
                             if blame:
                                 bd = 'working directory'
                                 if not blamecache:
                                     blamecache = getblame(f)
                                 if n < len(blamecache):
                                     bl, bu, br = blamecache[n]
                                     if bl == l:
                                         bd = '%s@%s' % (bu, br)
                             errors.append((f, lineno and n + 1, l, msg, bd))
                             result = False
                     errors.sort()
                     for e in errors:
                         logfunc(*e)
                         fc += 1
                         if maxerr and fc >= maxerr:
                             print " (too many errors, giving up)"
                             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.add_option("-b", "--blame", action="store_true",
                                   help="use annotate to generate blame info")
                 parser.add_option("", "--debug", action="store_true",
                                   help="show debug information")
                 parser.add_option("", "--nolineno", action="store_false",
                                   dest='lineno', help="don't show line numbers")
                 parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                                     lineno=True)
                 (options, args) = parser.parse_args()
                 if len(args) == 0:
                     check = glob.glob("*")
                 else:
                     check = args
                 ret = 0
                 for f in check:
                     if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                                      blame=options.blame, debug=options.debug,
                                      lineno=options.lineno):
                         ret = 1
                 sys.exit(ret)