upstream/mercurial-mirror Commit - r34062:e267d4ee

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)

17

(you can append a short comment and match this, like: #re-raises)

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

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

def opentext(f):

32

def opentext(f):

33

return open(f, encoding='ascii')

33

return open(f, encoding='ascii')

34

try:

34

try:

35

xrange

35

xrange

36

except NameError:

36

except NameError:

37

xrange = range

37

xrange = range

38

try:

38

try:

39

import re2

39

import re2

40

except ImportError:

40

except ImportError:

41

re2 = None

41

re2 = None

42

43

def compilere(pat, multiline=False):

43

def compilere(pat, multiline=False):

44

if multiline:

44

if multiline:

45

pat = '(?m)' + pat

45

pat = '(?m)' + pat

46

if re2:

46

if re2:

47

try:

47

try:

48

return re2.compile(pat)

48

return re2.compile(pat)

49

except re2.error:

49

except re2.error:

50

pass

50

pass

51

return re.compile(pat)

51

return re.compile(pat)

52

53

# check "rules depending on implementation of repquote()" in each

53

# check "rules depending on implementation of repquote()" in each

54

# patterns (especially pypats), before changing around repquote()

54

# patterns (especially pypats), before changing around repquote()

55

_repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',

55

_repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',

56

'%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}

56

'%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}

57

def _repquoteencodechr(i):

57

def _repquoteencodechr(i):

58

if i > 255:

58

if i > 255:

59

return 'u'

59

return 'u'

60

c = chr(i)

60

c = chr(i)

61

if c in _repquotefixedmap:

61

if c in _repquotefixedmap:

62

return _repquotefixedmap[c]

62

return _repquotefixedmap[c]

63

if c.isalpha():

63

if c.isalpha():

64

return 'x'

64

return 'x'

65

if c.isdigit():

65

if c.isdigit():

66

return 'n'

66

return 'n'

67

return 'o'

67

return 'o'

68

_repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))

68

_repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))

69

70

def repquote(m):

70

def repquote(m):

71

t = m.group('text')

71

t = m.group('text')

72

t = t.translate(_repquotett)

72

t = t.translate(_repquotett)

73

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

73

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

74

75

def reppython(m):

75

def reppython(m):

76

comment = m.group('comment')

76

comment = m.group('comment')

77

if comment:

77

if comment:

78

l = len(comment.rstrip())

78

l = len(comment.rstrip())

79

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

79

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

80

return repquote(m)

80

return repquote(m)

81

82

def repcomment(m):

82

def repcomment(m):

83

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

83

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

84

85

def repccomment(m):

85

def repccomment(m):

86

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

86

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

87

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

87

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

88

89

def repcallspaces(m):

89

def repcallspaces(m):

90

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

90

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

91

return m.group(1) + t

91

return m.group(1) + t

92

93

def repinclude(m):

93

def repinclude(m):

94

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

94

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

95

96

def rephere(m):

96

def rephere(m):

97

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

97

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

98

return m.group(1) + t

98

return m.group(1) + t

99

100

101

testpats = [

101

testpats = [

102

[

102

[

103

(r'\b(push|pop)d\b', "don't use 'pushd' or 'popd', use 'cd'"),

103

(r'\b(push|pop)d\b', "don't use 'pushd' or 'popd', use 'cd'"),

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

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

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

(r'\[[^\]]+==', '[ foo == bar ] is a bashism, use [ foo = bar ] instead'),

119

(r'\[[^\]]+==', '[ foo == bar ] is a bashism, use [ foo = bar ] instead'),

120

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

120

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

121

"use egrep for extended grep syntax"),

121

"use egrep for extended grep syntax"),

122

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

122

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

123

(r'#!.*/bash', "don't use bash in shebang, use sh"),

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

(r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),

141

(r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),

141

(r'[\s="`\']python\s(?!bindings)', "don't use 'python', use '$PYTHON'"),

142

(r'[\s="`\']python\s(?!bindings)', "don't use 'python', use '$PYTHON'"),

142

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

143

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

143

(r'\butil\.Abort\b', "directly use error.Abort"),

144

(r'\butil\.Abort\b', "directly use error.Abort"),

144

(r'\|&', "don't use |&, use 2>&1"),

145

(r'\|&', "don't use |&, use 2>&1"),

145

(r'\w = +\w', "only one space after = allowed"),

146

(r'\w = +\w', "only one space after = allowed"),

146

(r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),

147

(r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),

147

(r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),

148

(r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),

148

(r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),

149

(r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),

149

(r'grep.* -[ABC] ', "don't use grep's context flags"),

150

(r'grep.* -[ABC] ', "don't use grep's context flags"),

150

],

151

],

151

# warnings

152

# warnings

152

[

153

[

153

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

154

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

154

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

155

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

155

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

156

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

156

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

157

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

157

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

158

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

158

]

159

]

159

]

160

]

160

161

testfilters = [

162

testfilters = [

162

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

163

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

163

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

164

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

164

]

165

]

165

166

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

167

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

167

uprefix = r"^ \$ "

168

uprefix = r"^ \$ "

168

utestpats = [

169

utestpats = [

169

[

170

[

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

"explicit exit code checks unnecessary"),

177

"explicit exit code checks unnecessary"),

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

winglobmsg),

185

winglobmsg),

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

(r'^ [^$>].*27\.0\.0\.1',

197

(r'^ [^$>].*27\.0\.0\.1',

197

'use $LOCALIP not an explicit loopback address'),

198

'use $LOCALIP not an explicit loopback address'),

198

(r'^ [^$>].*\$LOCALIP.*[^)]$',

199

(r'^ [^$>].*\$LOCALIP.*[^)]$',

199

'mark $LOCALIP output lines with (glob) to help tests in BSD jails'),

200

'mark $LOCALIP output lines with (glob) to help tests in BSD jails'),

200

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

201

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

201

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

202

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

202

(r'^ diff -[^ -]*p',

203

(r'^ diff -[^ -]*p',

203

"don't use (external) diff with -p for portability"),

204

"don't use (external) diff with -p for portability"),

204

(r'^ [-+][-+][-+] .* [-+]0000 $glob$',

205

(r'^ [-+][-+][-+] .* [-+]0000 $glob$',

205

"glob timezone field in diff output for portability"),

206

"glob timezone field in diff output for portability"),

206

(r'^ @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',

207

(r'^ @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',

207

"use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),

208

"use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),

208

(r'^ @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',

209

(r'^ @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',

209

"use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),

210

"use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),

210

(r'^ @@ -[0-9]+ [+][0-9]+ @@',

211

(r'^ @@ -[0-9]+ [+][0-9]+ @@',

211

"use '@@ -N* +N* @@ (glob)' style chunk header for portability"),

212

"use '@@ -N* +N* @@ (glob)' style chunk header for portability"),

212

(uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'

213

(uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'

213

r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',

214

r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',

214

"use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),

215

"use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),

215

],

216

],

216

# warnings

217

# warnings

217

[

218

[

218

(r'^ (?!.*\$LOCALIP)[^*?/\n]* $glob$$',

219

(r'^ (?!.*\$LOCALIP)[^*?/\n]* $glob$$',

219

"glob match with no glob string (?, *, /, and $LOCALIP)"),

220

"glob match with no glob string (?, *, /, and $LOCALIP)"),

220

]

221

]

221

]

222

]

222

223

for i in [0, 1]:

224

for i in [0, 1]:

224

for tp in testpats[i]:

225

for tp in testpats[i]:

225

p = tp[0]

226

p = tp[0]

226

m = tp[1]

227

m = tp[1]

227

if p.startswith(r'^'):

228

if p.startswith(r'^'):

228

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

229

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

229

else:

230

else:

230

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

231

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

231

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

232

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

232

233

utestfilters = [

234

utestfilters = [

234

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

235

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

235

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

236

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

236

]

237

]

237

238

pypats = [

239

pypats = [

239

[

240

[

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

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

247

'dict-from-generator'),

248

'dict-from-generator'),

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

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

256

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

257

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

257

(r'\w\s=\s\s+\w', "gratuitous whitespace after ="),

258

(r'\w\s=\s\s+\w', "gratuitous whitespace after ="),

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

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

262

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

263

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

263

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

264

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

264

"don't use camelcase in identifiers"),

265

"don't use camelcase in identifiers"),

265

266

266

"linebreak after :"),

267

"linebreak after :"),

267

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

268

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

268

r'#.*old-style'),

269

r'#.*old-style'),

269

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

270

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

270

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

271

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

271

r'#.*old-style'),

272

r'#.*old-style'),

272

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

273

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

273

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

274

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

274

"Python keyword is not a function"),

275

"Python keyword is not a function"),

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

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

280

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

281

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

281

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

282

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

282

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

283

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

283

"gratuitous whitespace after Python keyword"),

284

"gratuitous whitespace after Python keyword"),

284

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

285

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

285

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

286

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

286

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

287

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

287

"missing whitespace around operator"),

288

"missing whitespace around operator"),

288

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

289

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

289

"missing whitespace around operator"),

290

"missing whitespace around operator"),

290

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

291

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

291

"missing whitespace around operator"),

292

"missing whitespace around operator"),

292

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

293

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

293

"wrong whitespace around ="),

294

"wrong whitespace around ="),

294

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

295

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

295

"no whitespace around = for named parameters"),

296

"no whitespace around = for named parameters"),

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

(r'^\s*if False(:| +and)', 'Remove code instead of using `if False`'),

305

(r'^\s*if False(:| +and)', 'Remove code instead of using `if False`'),

305

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

306

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

306

'hasattr(foo, bar) is broken on py2, use util.safehasattr(foo, bar) '

307

'hasattr(foo, bar) is broken on py2, use util.safehasattr(foo, bar) '

307

'instead', r'#.*hasattr-py3-only'),

308

'instead', r'#.*hasattr-py3-only'),

308

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

309

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

309

"use opener.read() instead"),

310

"use opener.read() instead"),

310

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

311

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

311

"use opener.write() instead"),

312

"use opener.write() instead"),

312

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

313

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

313

"use util.readfile() instead"),

314

"use util.readfile() instead"),

314

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

315

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

315

"use util.writefile() instead"),

316

"use util.writefile() instead"),

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

(r'\bdef\s+__bool__\b', "__bool__ should be __nonzero__ in Python 2"),

329

(r'\bdef\s+__bool__\b', "__bool__ should be __nonzero__ in Python 2"),

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

(r'\butil\.Abort\b', "directly use error.Abort"),

335

(r'\butil\.Abort\b', "directly use error.Abort"),

335

(r'^@(\w*\.)?cachefunc', "module-level @cachefunc is risky, please avoid"),

336

(r'^@(\w*\.)?cachefunc', "module-level @cachefunc is risky, please avoid"),

336

(r'^import Queue', "don't use Queue, use util.queue + util.empty"),

337

(r'^import Queue', "don't use Queue, use util.queue + util.empty"),

337

(r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),

338

(r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),

338

(r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),

339

(r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),

339

(r'^import SocketServer', "don't use SockerServer, use util.socketserver"),

340

(r'^import SocketServer', "don't use SockerServer, use util.socketserver"),

340

(r'^import urlparse', "don't use urlparse, use util.urlreq"),

341

(r'^import urlparse', "don't use urlparse, use util.urlreq"),

341

(r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),

342

(r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),

342

(r'^import cPickle', "don't use cPickle, use util.pickle"),

343

(r'^import cPickle', "don't use cPickle, use util.pickle"),

343

(r'^import pickle', "don't use pickle, use util.pickle"),

344

(r'^import pickle', "don't use pickle, use util.pickle"),

344

(r'^import httplib', "don't use httplib, use util.httplib"),

345

(r'^import httplib', "don't use httplib, use util.httplib"),

345

(r'^import BaseHTTPServer', "use util.httpserver instead"),

346

(r'^import BaseHTTPServer', "use util.httpserver instead"),

346

(r'^(from|import) mercurial\.(cext|pure|cffi)',

347

(r'^(from|import) mercurial\.(cext|pure|cffi)',

347

"use mercurial.policy.importmod instead"),

348

"use mercurial.policy.importmod instead"),

348

(r'\.next', "don't use .next(), use next(...)"),

349

(r'\.next', "don't use .next(), use next(...)"),

349

(r'([a-z]*).revision\(\1\.node\(',

350

(r'([a-z]*).revision\(\1\.node\(',

350

"don't convert rev to node before passing to revision(nodeorrev)"),

351

"don't convert rev to node before passing to revision(nodeorrev)"),

351

352

# rules depending on implementation of repquote()

353

# rules depending on implementation of repquote()

353

(r' x+[xpqo%APM][\'"]\n\s+[\'"]x',

354

(r' x+[xpqo%APM][\'"]\n\s+[\'"]x',

354

'string join across lines with no space'),

355

'string join across lines with no space'),

355

(r'''(?x)ui\.(status|progress|write|note|warn)\(

356

(r'''(?x)ui\.(status|progress|write|note|warn)\(

356

[ \t\n#]*

357

[ \t\n#]*

357

(?# any strings/comments might precede a string, which

358

(?# any strings/comments might precede a string, which

358

# contains translatable message)

359

# contains translatable message)

359

((['"]|\'\'\'|""")[ \npq%bAPMxno]*(['"]|\'\'\'|""")[ \t\n#]+)*

360

((['"]|\'\'\'|""")[ \npq%bAPMxno]*(['"]|\'\'\'|""")[ \t\n#]+)*

360

(?# sequence consisting of below might precede translatable message

361

(?# sequence consisting of below might precede translatable message

361

# - formatting string: "% 10s", "%05d", "% -3.2f", "%*s", "%%" ...

362

# - formatting string: "% 10s", "%05d", "% -3.2f", "%*s", "%%" ...

362

# - escaped character: "\\", "\n", "\0" ...

363

# - escaped character: "\\", "\n", "\0" ...

363

# - character other than '%', 'b' as '\', and 'x' as alphabet)

364

# - character other than '%', 'b' as '\', and 'x' as alphabet)

364

(['"]|\'\'\'|""")

365

(['"]|\'\'\'|""")

365

((%([ n]?[PM]?([np]+|A))?x)|%%|b[bnx]|[ \nnpqAPMo])*x

366

((%([ n]?[PM]?([np]+|A))?x)|%%|b[bnx]|[ \nnpqAPMo])*x

366

(?# this regexp can't use [^...] style,

367

(?# this regexp can't use [^...] style,

367

# because _preparepats forcibly adds "\n" into [^...],

368

# because _preparepats forcibly adds "\n" into [^...],

368

# even though this regexp wants match it against "\n")''',

369

# even though this regexp wants match it against "\n")''',

369

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

370

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

370

],

371

],

371

# warnings

372

# warnings

372

[

373

[

373

# rules depending on implementation of repquote()

374

# rules depending on implementation of repquote()

374

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

375

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

375

]

376

]

376

]

377

]

377

378

pyfilters = [

379

pyfilters = [

379

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

380

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

380

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

381

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

381

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

382

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

382

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

383

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

383

]

384

]

384

385

# extension non-filter patterns

386

# extension non-filter patterns

386

pyextnfpats = [

387

pyextnfpats = [

387

[(r'^"""\n?[A-Z]', "don't capitalize docstring title")],

388

[(r'^"""\n?[A-Z]', "don't capitalize docstring title")],

388

# warnings

389

# warnings

389

[],

390

[],

390

]

391

]

391

392

txtfilters = []

393

txtfilters = []

393

394

txtpats = [

395

txtpats = [

395

[

396

[

396

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

397

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

397

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

398

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

398

],

399

],

399

[]

400

[]

400

]

401

]

401

402

cpats = [

403

cpats = [

403

[

404

[

404

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

405

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

405

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

406

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

406

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

407

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

407

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

408

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

408

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

409

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

409

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

410

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

410

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

411

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

411

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

412

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

412

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

413

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

413

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

414

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

414

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

415

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

415

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

416

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

416

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

417

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

417

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

418

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

418

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

419

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

419

(r'\w\s=\s\s+\w', "gratuitous whitespace after ="),

420

(r'\w\s=\s\s+\w', "gratuitous whitespace after ="),

420

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

421

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

421

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

422

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

422

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

423

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

423

(r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),

424

(r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),

424

(r'strcat\(', "don't use strcat"),

425

(r'strcat\(', "don't use strcat"),

425

426

# rules depending on implementation of repquote()

427

# rules depending on implementation of repquote()

427

],

428

],

428

# warnings

429

# warnings

429

[

430

[

430

# rules depending on implementation of repquote()

431

# rules depending on implementation of repquote()

431

]

432

]

432

]

433

]

433

434

cfilters = [

435

cfilters = [

435

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

436

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

436

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

437

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

437

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

438

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

438

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

439

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

439

]

440

]

440

441

inutilpats = [

442

inutilpats = [

442

[

443

[

443

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

444

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

444

],

445

],

445

# warnings

446

# warnings

446

[]

447

[]

447

]

448

]

448

449

inrevlogpats = [

450

inrevlogpats = [

450

[

451

[

451

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

452

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

452

],

453

],

453

# warnings

454

# warnings

454

[]

455

[]

455

]

456

]

456

457

webtemplatefilters = []

458

webtemplatefilters = []

458

459

webtemplatepats = [

460

webtemplatepats = [

460

[],

461

[],

461

[

462

[

462

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

463

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

463

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

464

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

464

]

465

]

465

]

466

]

466

467

allfilesfilters = []

468

allfilesfilters = []

468

469

allfilespats = [

470

allfilespats = [

470

[

471

[

471

(r'(http|https)://[a-zA-Z0-9./]*selenic.com/',

472

(r'(http|https)://[a-zA-Z0-9./]*selenic.com/',

472

'use mercurial-scm.org domain URL'),

473

'use mercurial-scm.org domain URL'),

473

(r'mercurial@selenic\.com',

474

(r'mercurial@selenic\.com',

474

'use mercurial-scm.org domain for mercurial ML address'),

475

'use mercurial-scm.org domain for mercurial ML address'),

475

(r'mercurial-devel@selenic\.com',

476

(r'mercurial-devel@selenic\.com',

476

'use mercurial-scm.org domain for mercurial-devel ML address'),

477

'use mercurial-scm.org domain for mercurial-devel ML address'),

477

],

478

],

478

# warnings

479

# warnings

479

[],

480

[],

480

]

481

]

481

482

py3pats = [

483

py3pats = [

483

[

484

[

484

(r'os\.environ', "use encoding.environ instead (py3)", r'#.*re-exports'),

485

(r'os\.environ', "use encoding.environ instead (py3)", r'#.*re-exports'),

485

(r'os\.name', "use pycompat.osname instead (py3)"),

486

(r'os\.name', "use pycompat.osname instead (py3)"),

486

(r'os\.getcwd', "use pycompat.getcwd instead (py3)"),

487

(r'os\.getcwd', "use pycompat.getcwd instead (py3)"),

487

(r'os\.sep', "use pycompat.ossep instead (py3)"),

488

(r'os\.sep', "use pycompat.ossep instead (py3)"),

488

(r'os\.pathsep', "use pycompat.ospathsep instead (py3)"),

489

(r'os\.pathsep', "use pycompat.ospathsep instead (py3)"),

489

(r'os\.altsep', "use pycompat.osaltsep instead (py3)"),

490

(r'os\.altsep', "use pycompat.osaltsep instead (py3)"),

490

(r'sys\.platform', "use pycompat.sysplatform instead (py3)"),

491

(r'sys\.platform', "use pycompat.sysplatform instead (py3)"),

491

(r'getopt\.getopt', "use pycompat.getoptb instead (py3)"),

492

(r'getopt\.getopt', "use pycompat.getoptb instead (py3)"),

492

(r'os\.getenv', "use encoding.environ.get instead"),

493

(r'os\.getenv', "use encoding.environ.get instead"),

493

(r'os\.setenv', "modifying the environ dict is not preferred"),

494

(r'os\.setenv', "modifying the environ dict is not preferred"),

494

],

495

],

495

# warnings

496

# warnings

496

[],

497

[],

497

]

498

]

498

499

checks = [

500

checks = [

500

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

501

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

501

('python', r'.*hgext.*\.py$', '', [], pyextnfpats),

502

('python', r'.*hgext.*\.py$', '', [], pyextnfpats),

502

('python 3', r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',

503

('python 3', r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',

503

'', pyfilters, py3pats),

504

'', pyfilters, py3pats),

504

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

505

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

505

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

506

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

506

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

507

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

507

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

508

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

508

pyfilters, inrevlogpats),

509

pyfilters, inrevlogpats),

509

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

510

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

510

inutilpats),

511

inutilpats),

511

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

512

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

512

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

513

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

513

webtemplatefilters, webtemplatepats),

514

webtemplatefilters, webtemplatepats),

514

('all except for .po', r'.*(?<!\.po)$', '',

515

('all except for .po', r'.*(?<!\.po)$', '',

515

allfilesfilters, allfilespats),

516

allfilesfilters, allfilespats),

516

]

517

]

517

518

def _preparepats():

519

def _preparepats():

519

for c in checks:

520

for c in checks:

520

failandwarn = c[-1]

521

failandwarn = c[-1]

521

for pats in failandwarn:

522

for pats in failandwarn:

522

for i, pseq in enumerate(pats):

523

for i, pseq in enumerate(pats):

523

# fix-up regexes for multi-line searches

524

# fix-up regexes for multi-line searches

524

p = pseq[0]

525

p = pseq[0]

525

# \s doesn't match \n

526

# \s doesn't match \n

526

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

527

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

527

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

528

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

528

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

529

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

529

530

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

531

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

531

filters = c[3]

532

filters = c[3]

532

for i, flt in enumerate(filters):

533

for i, flt in enumerate(filters):

533

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

534

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

534

535

class norepeatlogger(object):

536

class norepeatlogger(object):

536

def __init__(self):

537

def __init__(self):

537

self._lastseen = None

538

self._lastseen = None

538

539

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

540

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

540

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

541

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

541

542

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

543

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

543

of multiple errors.

544

of multiple errors.

544

545

:fname: filename

546

:fname: filename

546

:lineno: line number

547

:lineno: line number

547

:line: actual content of the line

548

:line: actual content of the line

548

:msg: error message

549

:msg: error message

549

"""

550

"""

550

msgid = fname, lineno, line

551

msgid = fname, lineno, line

551

if msgid != self._lastseen:

552

if msgid != self._lastseen:

552

if blame:

553

if blame:

553

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

554

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

554

else:

555

else:

555

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

556

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

556

print(" > %s" % line)

557

print(" > %s" % line)

557

self._lastseen = msgid

558

self._lastseen = msgid

558

print(" " + msg)

559

print(" " + msg)

559

560

_defaultlogger = norepeatlogger()

561

_defaultlogger = norepeatlogger()

561

562

def getblame(f):

563

def getblame(f):

563

lines = []

564

lines = []

564

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

565

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

565

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

566

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

566

user, rev = start.split()

567

user, rev = start.split()

567

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

568

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

568

return lines

569

return lines

569

570

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

571

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

571

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

572

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

572

"""checks style and portability of a given file

573

"""checks style and portability of a given file

573

574

:f: filepath

575

:f: filepath

575

:logfunc: function used to report error

576

:logfunc: function used to report error

576

logfunc(filename, linenumber, linecontent, errormessage)

577

logfunc(filename, linenumber, linecontent, errormessage)

577

:maxerr: number of error to display before aborting.

578

:maxerr: number of error to display before aborting.

578

Set to false (default) to report all errors

579

Set to false (default) to report all errors

579

580

return True if no error is found, False otherwise.

581

return True if no error is found, False otherwise.

581

"""

582

"""

582

blamecache = None

583

blamecache = None

583

result = True

584

result = True

584

585

try:

586

try:

586

with opentext(f) as fp:

587

with opentext(f) as fp:

587

try:

588

try:

588

pre = post = fp.read()

589

pre = post = fp.read()

589

except UnicodeDecodeError as e:

590

except UnicodeDecodeError as e:

590

print("%s while reading %s" % (e, f))

591

print("%s while reading %s" % (e, f))

591

return result

592

return result

592

except IOError as e:

593

except IOError as e:

593

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

594

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

594

return result

595

return result

595

596

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

597

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

597

post = pre # discard filtering result of previous check

598

post = pre # discard filtering result of previous check

598

if debug:

599

if debug:

599

print(name, f)

600

print(name, f)

600

fc = 0

601

fc = 0

601

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

602

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

602

if debug:

603

if debug:

603

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

604

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

604

name, match, f))

605

name, match, f))

605

continue

606

continue

606

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

607

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

607

# If you're looking at this line, it's because a file has:

608

# If you're looking at this line, it's because a file has:

608

# no- check- code

609

# no- check- code

609

# but the reason to output skipping is to make life for

610

# but the reason to output skipping is to make life for

610

# tests easier. So, instead of writing it with a normal

611

# tests easier. So, instead of writing it with a normal

611

# spelling, we write it with the expected spelling from

612

# spelling, we write it with the expected spelling from

612

# tests/test-check-code.t

613

# tests/test-check-code.t

613

print("Skipping %s it has no-che?k-code (glob)" % f)

614

print("Skipping %s it has no-che?k-code (glob)" % f)

614

return "Skip" # skip checking this file

615

return "Skip" # skip checking this file

615

for p, r in filters:

616

for p, r in filters:

616

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

617

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

617

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

618

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

618

if warnings:

619

if warnings:

619

pats = pats[0] + pats[1]

620

pats = pats[0] + pats[1]

620

else:

621

else:

621

pats = pats[0]

622

pats = pats[0]

622

# print post # uncomment to show filtered version

623

# print post # uncomment to show filtered version

623

624

if debug:

625

if debug:

625

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

626

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

626

627

prelines = None

628

prelines = None

628

errors = []

629

errors = []

629

for i, pat in enumerate(pats):

630

for i, pat in enumerate(pats):

630

if len(pat) == 3:

631

if len(pat) == 3:

631

p, msg, ignore = pat

632

p, msg, ignore = pat

632

else:

633

else:

633

p, msg = pat

634

p, msg = pat

634

ignore = None

635

ignore = None

635

if i >= nerrs:

636

if i >= nerrs:

636

msg = "warning: " + msg

637

msg = "warning: " + msg

637

638

pos = 0

639

pos = 0

639

n = 0

640

n = 0

640

for m in p.finditer(post):

641

for m in p.finditer(post):

641

if prelines is None:

642

if prelines is None:

642

prelines = pre.splitlines()

643

prelines = pre.splitlines()

643

postlines = post.splitlines(True)

644

postlines = post.splitlines(True)

644

645

start = m.start()

646

start = m.start()

646

while n < len(postlines):

647

while n < len(postlines):

647

step = len(postlines[n])

648

step = len(postlines[n])

648

if pos + step > start:

649

if pos + step > start:

649

break

650

break

650

pos += step

651

pos += step

651

n += 1

652

n += 1

652

l = prelines[n]

653

l = prelines[n]

653

654

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

655

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

655

if debug:

656

if debug:

656

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

657

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

657

name, f, n))

658

name, f, n))

658

continue

659

continue

659

bd = ""

660

bd = ""

660

if blame:

661

if blame:

661

bd = 'working directory'

662

bd = 'working directory'

662

if not blamecache:

663

if not blamecache:

663

blamecache = getblame(f)

664

blamecache = getblame(f)

664

if n < len(blamecache):

665

if n < len(blamecache):

665

bl, bu, br = blamecache[n]

666

bl, bu, br = blamecache[n]

666

if bl == l:

667

if bl == l:

667

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

668

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

668

669

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

670

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

670

result = False

671

result = False

671

672

errors.sort()

673

errors.sort()

673

for e in errors:

674

for e in errors:

674

logfunc(*e)

675

logfunc(*e)

675

fc += 1

676

fc += 1

676

if maxerr and fc >= maxerr:

677

if maxerr and fc >= maxerr:

677

print(" (too many errors, giving up)")

678

print(" (too many errors, giving up)")

678

break

679

break

679

680

return result

681

return result

681

682

def main():

683

def main():

683

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

684

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

684

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

685

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

685

help="include warning-level checks")

686

help="include warning-level checks")

686

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

687

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

687

help="max warnings per file")

688

help="max warnings per file")

688

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

689

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

689

help="use annotate to generate blame info")

690

help="use annotate to generate blame info")

690

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

691

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

691

help="show debug information")

692

help="show debug information")

692

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

693

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

693

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

694

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

694

695

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

696

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

696

lineno=True)

697

lineno=True)

697

(options, args) = parser.parse_args()

698

(options, args) = parser.parse_args()

698

699

if len(args) == 0:

700

if len(args) == 0:

700

check = glob.glob("*")

701

check = glob.glob("*")

701

elif args == ['-']:

702

elif args == ['-']:

702

# read file list from stdin

703

# read file list from stdin

703

check = sys.stdin.read().splitlines()

704

check = sys.stdin.read().splitlines()

704

else:

705

else:

705

check = args

706

check = args

706

707

_preparepats()

708

_preparepats()

708

709

ret = 0

710

ret = 0

710

for f in check:

711

for f in check:

711

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

712

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

712

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

713

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

713

lineno=options.lineno):

714

lineno=options.lineno):

714

ret = 1

715

ret = 1

715

return ret

716

return ret

716

717

if __name__ == "__main__":

718

if __name__ == "__main__":

718

sys.exit(main())

719

sys.exit(main())

	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)
              * 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
             """
             from __future__ import absolute_import, print_function
             import glob
             import keyword
             import optparse
             import os
             import re
             import sys
             if sys.version_info[0] < 3:
                 opentext = open
             else:
                 def opentext(f):
                     return open(f, encoding='ascii')
             try:
                 xrange
             except NameError:
                 xrange = range
             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)
             # check "rules depending on implementation of repquote()" in each
             # patterns (especially pypats), before changing around repquote()
             _repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
                                  '%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}
             def _repquoteencodechr(i):
                 if i > 255:
                     return 'u'
                 c = chr(i)
                 if c in _repquotefixedmap:
                     return _repquotefixedmap[c]
                 if c.isalpha():
                     return 'x'
                 if c.isdigit():
                     return 'n'
                 return 'o'
             _repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))
             def repquote(m):
                 t = m.group('text')
                 t = t.translate(_repquotett)
                 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'\b(push|pop)d\b', "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)', r"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'\[[^\]]+==', '[ foo == bar ] is a bashism, use [ foo = bar ] instead'),
                 (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                  "use egrep for extended grep syntax"),
-                (r'/bin/', "don't use explicit paths for tools"),
+                (r'(?<!!)/bin/', "don't use explicit paths for tools"),
+                (r'#!.*/bash', "don't use bash in shebang, use sh"),
                 (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'\bls +[^|\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*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
                 (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
                 (r'[\s="`\']python\s(?!bindings)', "don't use 'python', use '$PYTHON'"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'\|&', "don't use |&, use 2>&1"),
                 (r'\w =  +\w', "only one space after = allowed"),
                 (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
                 (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),
                 (r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),
                 (r'grep.* -[ABC] ', "don't use grep's context flags"),
               ],
               # 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"( *)(#([^!][^\n]*\S)?)", repcomment),
                 (r"<<(\S+)((.|\n)*?\n\1)", rephere),
             ]
             winglobmsg = "use (glob) to match Windows paths too"
             uprefix = r"^  \$ "
             utestpats = [
               [
                 (r'^(\S.*||  [$>] \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'^  [^$>].*27\.0\.0\.1',
                  'use $LOCALIP not an explicit loopback address'),
                 (r'^  [^$>].*\$LOCALIP.*[^)]$',
                  'mark $LOCALIP output lines with (glob) to help tests in BSD jails'),
                 (r'^  (cat|find): .*: No such file or directory',
                  'use test -f to test for file existence'),
                 (r'^  diff -[^ -]*p',
                  "don't use (external) diff with -p for portability"),
                 (r'^  [-+][-+][-+] .* [-+]0000 \(glob\)',
                  "glob timezone field in diff output for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',
                  "use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N* +N* @@ (glob)' style chunk header for portability"),
                 (uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'
                  r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',
                  "use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),
               ],
               # warnings
               [
                 (r'^  (?!.*\$LOCALIP)[^*?/\n]* \(glob\)$',
                  "glob match with no glob string (?, *, /, and $LOCALIP)"),
               ]
             ]
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%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),
+                (r"( +)(#([^!][^\n]*\S)?)", repcomment),
             ]
             pypats = [
               [
                 (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'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
                 (r'(?<!\.)\breduce\s*\(.*', "reduce is not available in Python 3+"),
                 (r'\bdict\(.*=', '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'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'.{81}', "line too long"),
                 (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'#.*old-style'),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)",
                  r'#.*old-style'),
                 (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'^\s*if False(:| +and)', 'Remove code instead of using `if False`'),
                 (r'(?:(?<!def)\s+|\()hasattr\(',
                  'hasattr(foo, bar) is broken on py2, use util.safehasattr(foo, bar) '
                  'instead', r'#.*hasattr-py3-only'),
                 (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'release\(.*wlock, .*lock\)', "wrong lock release order"),
                 (r'\bdef\s+__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"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'^@(\w*\.)?cachefunc', "module-level @cachefunc is risky, please avoid"),
                 (r'^import Queue', "don't use Queue, use util.queue + util.empty"),
                 (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),
                 (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
                 (r'^import SocketServer', "don't use SockerServer, use util.socketserver"),
                 (r'^import urlparse', "don't use urlparse, use util.urlreq"),
                 (r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),
                 (r'^import cPickle', "don't use cPickle, use util.pickle"),
                 (r'^import pickle', "don't use pickle, use util.pickle"),
                 (r'^import httplib', "don't use httplib, use util.httplib"),
                 (r'^import BaseHTTPServer', "use util.httpserver instead"),
                 (r'^(from|import) mercurial\.(cext|pure|cffi)',
                  "use mercurial.policy.importmod instead"),
                 (r'\.next\(\)', "don't use .next(), use next(...)"),
                 (r'([a-z]*).revision\(\1\.node\(',
                  "don't convert rev to node before passing to revision(nodeorrev)"),
                 # rules depending on implementation of repquote()
                 (r' x+[xpqo%APM][\'"]\n\s+[\'"]x',
                  'string join across lines with no space'),
                 (r'''(?x)ui\.(status|progress|write|note|warn)\(
                      [ \t\n#]*
                      (?# any strings/comments might precede a string, which
                        # contains translatable message)
                      ((['"]|\'\'\'|""")[ \npq%bAPMxno]*(['"]|\'\'\'|""")[ \t\n#]+)*
                      (?# sequence consisting of below might precede translatable message
                        # - formatting string: "% 10s", "%05d", "% -3.2f", "%*s", "%%" ...
                        # - escaped character: "\\", "\n", "\0" ...
                        # - character other than '%', 'b' as '\', and 'x' as alphabet)
                      (['"]|\'\'\'|""")
                      ((%([ n]?[PM]?([np]+|A))?x)|%%|b[bnx]|[ \nnpqAPMo])*x
                      (?# this regexp can't use [^...] style,
                        # because _preparepats forcibly adds "\n" into [^...],
                        # even though this regexp wants match it against "\n")''',
                  "missing _() in ui message (use () to hide false-positives)"),
               ],
               # warnings
               [
                 # rules depending on implementation of repquote()
                 (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
               ]
             ]
             pyfilters = [
                 (r"""(?msx)(?P<comment>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""", reppython),
             ]
             # extension non-filter patterns
             pyextnfpats = [
                 [(r'^"""\n?[A-Z]', "don't capitalize docstring title")],
                 # warnings
                 [],
             ]
             txtfilters = []
             txtpats = [
               [
                 ('\s$', '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'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'^#\s+\w', "use #foo, not # foo"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'^\s*#import\b', "use only #include in standard C code"),
                 (r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),
                 (r'strcat\(', "don't use strcat"),
                 # rules depending on implementation of repquote()
               ],
               # warnings
               [
                 # rules depending on implementation of repquote()
               ]
             ]
             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'),
               ]
             ]
             allfilesfilters = []
             allfilespats = [
               [
                 (r'(http|https)://[a-zA-Z0-9./]*selenic.com/',
                  'use mercurial-scm.org domain URL'),
                 (r'mercurial@selenic\.com',
                  'use mercurial-scm.org domain for mercurial ML address'),
                 (r'mercurial-devel@selenic\.com',
                  'use mercurial-scm.org domain for mercurial-devel ML address'),
               ],
               # warnings
               [],
             ]
             py3pats = [
               [
                 (r'os\.environ', "use encoding.environ instead (py3)", r'#.*re-exports'),
                 (r'os\.name', "use pycompat.osname instead (py3)"),
                 (r'os\.getcwd', "use pycompat.getcwd instead (py3)"),
                 (r'os\.sep', "use pycompat.ossep instead (py3)"),
                 (r'os\.pathsep', "use pycompat.ospathsep instead (py3)"),
                 (r'os\.altsep', "use pycompat.osaltsep instead (py3)"),
                 (r'sys\.platform', "use pycompat.sysplatform instead (py3)"),
                 (r'getopt\.getopt', "use pycompat.getoptb instead (py3)"),
                 (r'os\.getenv', "use encoding.environ.get instead"),
                 (r'os\.setenv', "modifying the environ dict is not preferred"),
               ],
               # warnings
               [],
             ]
             checks = [
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
                 ('python', r'.*hgext.*\.py$', '', [], pyextnfpats),
                 ('python 3', r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',
                  '', pyfilters, py3pats),
                 ('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),
                 ('all except for .po', r'.*(?<!\.po)$', '',
                  allfilesfilters, allfilespats),
             ]
             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]
             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:
                     with opentext(f) as fp:
                         try:
                             pre = post = fp.read()
                         except UnicodeDecodeError as e:
                             print("%s while reading %s" % (e, f))
                             return result
                 except IOError as e:
                     print("Skipping %s, %s" % (f, str(e).split(':', 1)[0]))
                     return result
                 for name, match, magic, filters, pats in checks:
                     post = pre # discard filtering result of previous check
                     if debug:
                         print(name, f)
                     fc = 0
                     if not (re.match(match, f) or (magic and re.search(magic, pre))):
                         if debug:
                             print("Skipping %s for %s it doesn't match %s" % (
                                    name, match, f))
                         continue
                     if "no-" "check-code" in pre:
                         # If you're looking at this line, it's because a file has:
                         # no- check- code
                         # but the reason to output skipping is to make life for
                         # tests easier. So, instead of writing it with a normal
                         # spelling, we write it with the expected spelling from
                         # tests/test-check-code.t
                         print("Skipping %s it has no-che?k-code (glob)" % 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
             def 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("*")
                 elif args == ['-']:
                     # read file list from stdin
                     check = sys.stdin.read().splitlines()
                 else:
                     check = args
                 _preparepats()
                 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
                 return ret
             if __name__ == "__main__":
                 sys.exit(main())