upstream/mercurial-mirror Commit - r25212:a39c35e8

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

117

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

118

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

118

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

119

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

119

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

120

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

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

],

126

],

127

# warnings

127

# warnings

128

[

128

[

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

]

134

]

135

]

135

]

136

137

testfilters = [

137

testfilters = [

138

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

138

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

139

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

139

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

140

]

140

]

141

142

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

142

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

143

uprefix = r"^ \$ "

143

uprefix = r"^ \$ "

144

utestpats = [

144

utestpats = [

145

[

145

[

146

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

146

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

147

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

147

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

148

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

148

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

149

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

149

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

150

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

150

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

151

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

151

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

152

"explicit exit code checks unnecessary"),

152

"explicit exit code checks unnecessary"),

153

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

153

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

154

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

154

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

155

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

155

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

156

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

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

winglobmsg),

160

winglobmsg),

161

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

161

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

162

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

162

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

163

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

163

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

164

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

164

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

165

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

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

],

174

],

175

# warnings

175

# warnings

176

[

176

[

177

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

177

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

178

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

178

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

179

]

179

]

180

]

180

]

181

182

for i in [0, 1]:

182

for i in [0, 1]:

183

for tp in testpats[i]:

183

for tp in testpats[i]:

184

p = tp[0]

184

p = tp[0]

185

m = tp[1]

185

m = tp[1]

186

if p.startswith(r'^'):

186

if p.startswith(r'^'):

187

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

187

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

188

else:

188

else:

189

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

189

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

190

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

190

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

191

192

utestfilters = [

192

utestfilters = [

193

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

193

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

194

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

194

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

195

]

195

]

196

197

pypats = [

197

pypats = [

198

[

198

[

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

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

207

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

208

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

208

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

209

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

209

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

210

'dict-from-generator'),

210

'dict-from-generator'),

211

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

211

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

212

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

212

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

213

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

213

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

214

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

214

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

215

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

215

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

216

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

216

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

217

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

217

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

218

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

218

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

219

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

219

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

220

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

220

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

221

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

221

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

222

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

222

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

223

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

223

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

224

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

224

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

225

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

225

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

226

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

226

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

227

"don't use camelcase in identifiers"),

227

"don't use camelcase in identifiers"),

228

228

229

"linebreak after :"),

229

"linebreak after :"),

230

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

230

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

231

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

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

"Python keyword is not a function"),

235

"Python keyword is not a function"),

236

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

236

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

237

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

237

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

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

"gratuitous whitespace after Python keyword"),

244

"gratuitous whitespace after Python keyword"),

244

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

245

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

245

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

246

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

246

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

247

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

247

"missing whitespace around operator"),

248

"missing whitespace around operator"),

248

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

249

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

249

"missing whitespace around operator"),

250

"missing whitespace around operator"),

250

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

251

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

251

"missing whitespace around operator"),

252

"missing whitespace around operator"),

252

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

253

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

253

"wrong whitespace around ="),

254

"wrong whitespace around ="),

254

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

255

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

255

"no whitespace around = for named parameters"),

256

"no whitespace around = for named parameters"),

256

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

257

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

257

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

258

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

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

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

262

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

263

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

263

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

264

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

264

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

265

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

265

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

266

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

266

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

267

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

267

"use opener.read() instead"),

268

"use opener.read() instead"),

268

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

269

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

269

"use opener.write() instead"),

270

"use opener.write() instead"),

270

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

271

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

271

"use util.readfile() instead"),

272

"use util.readfile() instead"),

272

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

273

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

273

"use util.writefile() instead"),

274

"use util.writefile() instead"),

274

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

275

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

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

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

280

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

281

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

281

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

282

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

282

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

283

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

283

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

284

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

284

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

285

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

285

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

286

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

286

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

287

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

287

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

288

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

288

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

289

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

289

],

290

],

290

# warnings

291

# warnings

291

[

292

[

292

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

293

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

293

]

294

]

294

]

295

]

295

296

pyfilters = [

297

pyfilters = [

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

]

302

]

302

303

txtfilters = []

304

txtfilters = []

304

305

txtpats = [

306

txtpats = [

306

[

307

[

307

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

308

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

308

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

309

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

309

],

310

],

310

[]

311

[]

311

]

312

]

312

313

cpats = [

314

cpats = [

314

[

315

[

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

],

334

],

334

# warnings

335

# warnings

335

[]

336

[]

336

]

337

]

337

338

cfilters = [

339

cfilters = [

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

]

344

]

344

345

inutilpats = [

346

inutilpats = [

346

[

347

[

347

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

348

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

348

],

349

],

349

# warnings

350

# warnings

350

[]

351

[]

351

]

352

]

352

353

inrevlogpats = [

354

inrevlogpats = [

354

[

355

[

355

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

356

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

356

],

357

],

357

# warnings

358

# warnings

358

[]

359

[]

359

]

360

]

360

361

webtemplatefilters = []

362

webtemplatefilters = []

362

363

webtemplatepats = [

364

webtemplatepats = [

364

[],

365

[],

365

[

366

[

366

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

367

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

367

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

368

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

368

]

369

]

369

]

370

]

370

371

checks = [

372

checks = [

372

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

373

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

373

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

374

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

374

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

375

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

375

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

376

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

376

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

377

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

377

pyfilters, inrevlogpats),

378

pyfilters, inrevlogpats),

378

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

379

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

379

inutilpats),

380

inutilpats),

380

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

381

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

381

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

382

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

382

webtemplatefilters, webtemplatepats),

383

webtemplatefilters, webtemplatepats),

383

]

384

]

384

385

def _preparepats():

386

def _preparepats():

386

for c in checks:

387

for c in checks:

387

failandwarn = c[-1]

388

failandwarn = c[-1]

388

for pats in failandwarn:

389

for pats in failandwarn:

389

for i, pseq in enumerate(pats):

390

for i, pseq in enumerate(pats):

390

# fix-up regexes for multi-line searches

391

# fix-up regexes for multi-line searches

391

p = pseq[0]

392

p = pseq[0]

392

# \s doesn't match \n

393

# \s doesn't match \n

393

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

394

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

394

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

395

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

395

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

396

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

396

397

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

398

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

398

filters = c[3]

399

filters = c[3]

399

for i, flt in enumerate(filters):

400

for i, flt in enumerate(filters):

400

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

401

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

401

_preparepats()

402

_preparepats()

402

403

class norepeatlogger(object):

404

class norepeatlogger(object):

404

def __init__(self):

405

def __init__(self):

405

self._lastseen = None

406

self._lastseen = None

406

407

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

408

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

408

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

409

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

409

410

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

411

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

411

of multiple errors.

412

of multiple errors.

412

413

:fname: filename

414

:fname: filename

414

:lineno: line number

415

:lineno: line number

415

:line: actual content of the line

416

:line: actual content of the line

416

:msg: error message

417

:msg: error message

417

"""

418

"""

418

msgid = fname, lineno, line

419

msgid = fname, lineno, line

419

if msgid != self._lastseen:

420

if msgid != self._lastseen:

420

if blame:

421

if blame:

421

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

422

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

422

else:

423

else:

423

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

424

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

424

print " > %s" % line

425

print " > %s" % line

425

self._lastseen = msgid

426

self._lastseen = msgid

426

print " " + msg

427

print " " + msg

427

428

_defaultlogger = norepeatlogger()

429

_defaultlogger = norepeatlogger()

429

430

def getblame(f):

431

def getblame(f):

431

lines = []

432

lines = []

432

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

433

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

433

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

434

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

434

user, rev = start.split()

435

user, rev = start.split()

435

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

436

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

436

return lines

437

return lines

437

438

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

439

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

439

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

440

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

440

"""checks style and portability of a given file

441

"""checks style and portability of a given file

441

442

:f: filepath

443

:f: filepath

443

:logfunc: function used to report error

444

:logfunc: function used to report error

444

logfunc(filename, linenumber, linecontent, errormessage)

445

logfunc(filename, linenumber, linecontent, errormessage)

445

:maxerr: number of error to display before aborting.

446

:maxerr: number of error to display before aborting.

446

Set to false (default) to report all errors

447

Set to false (default) to report all errors

447

448

return True if no error is found, False otherwise.

449

return True if no error is found, False otherwise.

449

"""

450

"""

450

blamecache = None

451

blamecache = None

451

result = True

452

result = True

452

453

try:

454

try:

454

fp = open(f)

455

fp = open(f)

455

except IOError, e:

456

except IOError, e:

456

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

457

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

457

return result

458

return result

458

pre = post = fp.read()

459

pre = post = fp.read()

459

fp.close()

460

fp.close()

460

461

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

462

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

462

if debug:

463

if debug:

463

print name, f

464

print name, f

464

fc = 0

465

fc = 0

465

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

466

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

466

if debug:

467

if debug:

467

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

468

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

468

name, match, f)

469

name, match, f)

469

continue

470

continue

470

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

471

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

471

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

472

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

472

return "Skip" # skip checking this file

473

return "Skip" # skip checking this file

473

for p, r in filters:

474

for p, r in filters:

474

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

475

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

475

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

476

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

476

if warnings:

477

if warnings:

477

pats = pats[0] + pats[1]

478

pats = pats[0] + pats[1]

478

else:

479

else:

479

pats = pats[0]

480

pats = pats[0]

480

# print post # uncomment to show filtered version

481

# print post # uncomment to show filtered version

481

482

if debug:

483

if debug:

483

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

484

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

484

485

prelines = None

486

prelines = None

486

errors = []

487

errors = []

487

for i, pat in enumerate(pats):

488

for i, pat in enumerate(pats):

488

if len(pat) == 3:

489

if len(pat) == 3:

489

p, msg, ignore = pat

490

p, msg, ignore = pat

490

else:

491

else:

491

p, msg = pat

492

p, msg = pat

492

ignore = None

493

ignore = None

493

if i >= nerrs:

494

if i >= nerrs:

494

msg = "warning: " + msg

495

msg = "warning: " + msg

495

496

pos = 0

497

pos = 0

497

n = 0

498

n = 0

498

for m in p.finditer(post):

499

for m in p.finditer(post):

499

if prelines is None:

500

if prelines is None:

500

prelines = pre.splitlines()

501

prelines = pre.splitlines()

501

postlines = post.splitlines(True)

502

postlines = post.splitlines(True)

502

503

start = m.start()

504

start = m.start()

504

while n < len(postlines):

505

while n < len(postlines):

505

step = len(postlines[n])

506

step = len(postlines[n])

506

if pos + step > start:

507

if pos + step > start:

507

break

508

break

508

pos += step

509

pos += step

509

n += 1

510

n += 1

510

l = prelines[n]

511

l = prelines[n]

511

512

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

513

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

513

if debug:

514

if debug:

514

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

515

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

515

name, f, n)

516

name, f, n)

516

continue

517

continue

517

bd = ""

518

bd = ""

518

if blame:

519

if blame:

519

bd = 'working directory'

520

bd = 'working directory'

520

if not blamecache:

521

if not blamecache:

521

blamecache = getblame(f)

522

blamecache = getblame(f)

522

if n < len(blamecache):

523

if n < len(blamecache):

523

bl, bu, br = blamecache[n]

524

bl, bu, br = blamecache[n]

524

if bl == l:

525

if bl == l:

525

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

526

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

526

527

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

528

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

528

result = False

529

result = False

529

530

errors.sort()

531

errors.sort()

531

for e in errors:

532

for e in errors:

532

logfunc(*e)

533

logfunc(*e)

533

fc += 1

534

fc += 1

534

if maxerr and fc >= maxerr:

535

if maxerr and fc >= maxerr:

535

print " (too many errors, giving up)"

536

print " (too many errors, giving up)"

536

break

537

break

537

538

return result

539

return result

539

540

if __name__ == "__main__":

541

if __name__ == "__main__":

541

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

542

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

542

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

543

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

543

help="include warning-level checks")

544

help="include warning-level checks")

544

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

545

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

545

help="max warnings per file")

546

help="max warnings per file")

546

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

547

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

547

help="use annotate to generate blame info")

548

help="use annotate to generate blame info")

548

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

549

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

549

help="show debug information")

550

help="show debug information")

550

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

551

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

551

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

552

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

552

553

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

554

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

554

lineno=True)

555

lineno=True)

555

(options, args) = parser.parse_args()

556

(options, args) = parser.parse_args()

556

557

if len(args) == 0:

558

if len(args) == 0:

558

check = glob.glob("*")

559

check = glob.glob("*")

559

else:

560

else:

560

check = args

561

check = args

561

562

ret = 0

563

ret = 0

563

for f in check:

564

for f in check:

564

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

565

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

565

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

566

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

566

lineno=options.lineno):

567

lineno=options.lineno):

567

ret = 1

568

ret = 1

568

sys.exit(ret)

569

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'^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':\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, '')"),
               ],
               # 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, 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)