upstream/mercurial-mirror Commit - r33288:f08a178a

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

(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"),

135

(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"),

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

(r'\spython\s(?!bindings)', "don't use 'python', use '$PYTHON'"),

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

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

146

(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'"),

147

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

148

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

148

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

149

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

149

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

150

],

150

],

151

# warnings

151

# warnings

152

[

152

[

153

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

153

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

154

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

154

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

155

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

155

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

156

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

156

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

157

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

157

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

158

]

158

]

159

]

159

]

160

161

testfilters = [

161

testfilters = [

162

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

162

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

163

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

163

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

164

]

164

]

165

166

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

166

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

167

uprefix = r"^ \$ "

167

uprefix = r"^ \$ "

168

utestpats = [

168

utestpats = [

169

[

169

[

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

"explicit exit code checks unnecessary"),

176

"explicit exit code checks unnecessary"),

177

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

177

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

178

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

178

(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 "

179

(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

180

"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

181

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

182

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

182

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

183

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

183

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

184

winglobmsg),

184

winglobmsg),

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

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

207

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

208

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

208

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

209

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

209

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

210

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

210

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

211

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

211

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

212

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

212

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

213

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

213

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

214

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

214

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

215

],

215

],

216

# warnings

216

# warnings

217

[

217

[

218

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

218

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

219

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

219

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

220

]

220

]

221

]

221

]

222

223

for i in [0, 1]:

223

for i in [0, 1]:

224

for tp in testpats[i]:

224

for tp in testpats[i]:

225

p = tp[0]

225

p = tp[0]

226

m = tp[1]

226

m = tp[1]

227

if p.startswith(r'^'):

227

if p.startswith(r'^'):

228

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

228

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

229

else:

229

else:

230

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

230

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

231

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

231

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

232

233

utestfilters = [

233

utestfilters = [

234

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

234

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

235

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

235

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

236

]

236

]

237

238

pypats = [

238

pypats = [

239

[

239

[

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

'dict-from-generator'),

247

'dict-from-generator'),

248

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

248

(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 !='),

249

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

250

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

250

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

251

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

251

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

252

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

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

254

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

255

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

255

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

256

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

256

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

257

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

257

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

258

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

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

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

262

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

263

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

263

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

264

"don't use camelcase in identifiers"),

264

"don't use camelcase in identifiers"),

265

265

266

"linebreak after :"),

266

"linebreak after :"),

267

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

267

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

268

r'#.*old-style'),

268

r'#.*old-style'),

269

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

269

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

270

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

270

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

271

r'#.*old-style'),

271

r'#.*old-style'),

272

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

272

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

273

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

273

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

274

"Python keyword is not a function"),

274

"Python keyword is not a function"),

275

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

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

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

280

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

281

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

281

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

282

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

282

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

283

"gratuitous whitespace after Python keyword"),

283

"gratuitous whitespace after Python keyword"),

284

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

284

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

285

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

285

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

286

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

286

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

287

"missing whitespace around operator"),

287

"missing whitespace around operator"),

288

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

288

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

289

"missing whitespace around operator"),

289

"missing whitespace around operator"),

290

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

290

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

291

"missing whitespace around operator"),

291

"missing whitespace around operator"),

292

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

292

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

293

"wrong whitespace around ="),

293

"wrong whitespace around ="),

294

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

294

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

295

"no whitespace around = for named parameters"),

295

"no whitespace around = for named parameters"),

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

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

306

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

306

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

307

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

307

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

308

"use opener.read() instead"),

308

"use opener.read() instead"),

309

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

309

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

310

"use opener.write() instead"),

310

"use opener.write() instead"),

311

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

311

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

312

"use util.readfile() instead"),

312

"use util.readfile() instead"),

313

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

313

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

314

"use util.writefile() instead"),

314

"use util.writefile() instead"),

315

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

315

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

316

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

316

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

317

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

317

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

318

"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"),

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

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

337

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

337

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

338

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

338

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

339

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

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

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

344

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

344

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

345

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

345

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

346

"use mercurial.policy.importmod instead"),

346

"use mercurial.policy.importmod instead"),

347

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

347

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

348

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

348

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

349

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

349

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

350

351

# rules depending on implementation of repquote()

351

# rules depending on implementation of repquote()

352

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

352

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

353

'string join across lines with no space'),

353

'string join across lines with no space'),

354

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

354

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

355

[ \t\n#]*

355

[ \t\n#]*

356

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

356

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

357

# contains translatable message)

357

# contains translatable message)

358

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

358

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

359

(?# sequence consisting of below might precede translatable message

359

(?# sequence consisting of below might precede translatable message

360

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

360

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

361

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

361

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

362

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

362

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

363

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

363

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

364

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

364

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

365

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

365

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

366

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

366

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

367

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

367

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

368

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

368

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

369

],

369

],

370

# warnings

370

# warnings

371

[

371

[

372

# rules depending on implementation of repquote()

372

# rules depending on implementation of repquote()

373

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

373

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

374

]

374

]

375

]

375

]

376

377

pyfilters = [

377

pyfilters = [

378

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

378

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

379

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

379

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

380

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

380

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

381

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

381

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

382

]

382

]

383

384

# extension non-filter patterns

384

# extension non-filter patterns

385

pyextnfpats = [

385

pyextnfpats = [

386

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

386

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

387

# warnings

387

# warnings

388

[],

388

[],

389

]

389

]

390

391

txtfilters = []

391

txtfilters = []

392

393

txtpats = [

393

txtpats = [

394

[

394

[

395

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

395

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

396

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

396

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

397

],

397

],

398

[]

398

[]

399

]

399

]

400

401

cpats = [

401

cpats = [

402

[

402

[

403

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

403

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

404

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

404

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

405

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

405

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

406

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

406

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

407

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

407

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

408

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

408

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

409

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

409

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

410

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

410

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

411

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

411

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

412

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

412

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

413

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

413

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

414

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

414

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

415

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

415

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

416

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

416

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

417

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

417

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

418

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

418

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

419

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

419

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

420

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

420

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

421

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

421

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

422

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

422

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

423

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

423

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

424

425

# rules depending on implementation of repquote()

425

# rules depending on implementation of repquote()

426

],

426

],

427

# warnings

427

# warnings

428

[

428

[

429

# rules depending on implementation of repquote()

429

# rules depending on implementation of repquote()

430

]

430

]

431

]

431

]

432

433

cfilters = [

433

cfilters = [

434

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

434

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

435

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

435

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

436

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

436

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

437

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

437

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

438

]

438

]

439

440

inutilpats = [

440

inutilpats = [

441

[

441

[

442

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

442

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

443

],

443

],

444

# warnings

444

# warnings

445

[]

445

[]

446

]

446

]

447

448

inrevlogpats = [

448

inrevlogpats = [

449

[

449

[

450

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

450

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

451

],

451

],

452

# warnings

452

# warnings

453

[]

453

[]

454

]

454

]

455

456

webtemplatefilters = []

456

webtemplatefilters = []

457

458

webtemplatepats = [

458

webtemplatepats = [

459

[],

459

[],

460

[

460

[

461

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

461

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

462

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

462

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

463

]

463

]

464

]

464

]

465

466

allfilesfilters = []

466

allfilesfilters = []

467

468

allfilespats = [

468

allfilespats = [

469

[

469

[

470

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

470

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

471

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

471

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

472

(r'mercurial@selenic\.com',

472

(r'mercurial@selenic\.com',

473

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

473

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

474

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

474

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

475

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

475

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

476

],

476

],

477

# warnings

477

# warnings

478

[],

478

[],

479

]

479

]

480

481

py3pats = [

481

py3pats = [

482

[

482

[

483

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

483

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

484

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

484

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

485

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

485

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

486

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

486

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

487

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

487

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

488

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

488

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

489

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

489

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

490

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

490

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

491

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

491

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

492

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

492

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

493

],

493

],

494

# warnings

494

# warnings

495

[],

495

[],

496

]

496

]

497

498

checks = [

498

checks = [

499

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

499

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

500

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

500

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

501

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

501

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

502

'', pyfilters, py3pats),

502

'', pyfilters, py3pats),

503

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

503

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

504

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

504

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

505

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

505

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

506

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

506

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

507

pyfilters, inrevlogpats),

507

pyfilters, inrevlogpats),

508

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

508

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

509

inutilpats),

509

inutilpats),

510

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

510

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

511

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

511

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

512

webtemplatefilters, webtemplatepats),

512

webtemplatefilters, webtemplatepats),

513

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

513

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

514

allfilesfilters, allfilespats),

514

allfilesfilters, allfilespats),

515

]

515

]

516

517

def _preparepats():

517

def _preparepats():

518

for c in checks:

518

for c in checks:

519

failandwarn = c[-1]

519

failandwarn = c[-1]

520

for pats in failandwarn:

520

for pats in failandwarn:

521

for i, pseq in enumerate(pats):

521

for i, pseq in enumerate(pats):

522

# fix-up regexes for multi-line searches

522

# fix-up regexes for multi-line searches

523

p = pseq[0]

523

p = pseq[0]

524

# \s doesn't match \n

524

# \s doesn't match \n

525

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

525

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

526

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

526

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

527

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

527

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

528

529

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

529

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

530

filters = c[3]

530

filters = c[3]

531

for i, flt in enumerate(filters):

531

for i, flt in enumerate(filters):

532

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

532

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

533

534

class norepeatlogger(object):

534

class norepeatlogger(object):

535

def __init__(self):

535

def __init__(self):

536

self._lastseen = None

536

self._lastseen = None

537

538

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

538

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

539

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

539

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

540

541

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

541

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

542

of multiple errors.

542

of multiple errors.

543

544

:fname: filename

544

:fname: filename

545

:lineno: line number

545

:lineno: line number

546

:line: actual content of the line

546

:line: actual content of the line

547

:msg: error message

547

:msg: error message

548

"""

548

"""

549

msgid = fname, lineno, line

549

msgid = fname, lineno, line

550

if msgid != self._lastseen:

550

if msgid != self._lastseen:

551

if blame:

551

if blame:

552

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

552

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

553

else:

553

else:

554

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

554

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

555

print(" > %s" % line)

555

print(" > %s" % line)

556

self._lastseen = msgid

556

self._lastseen = msgid

557

print(" " + msg)

557

print(" " + msg)

558

559

_defaultlogger = norepeatlogger()

559

_defaultlogger = norepeatlogger()

560

561

def getblame(f):

561

def getblame(f):

562

lines = []

562

lines = []

563

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

563

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

564

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

564

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

565

user, rev = start.split()

565

user, rev = start.split()

566

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

566

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

567

return lines

567

return lines

568

569

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

569

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

570

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

570

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

571

"""checks style and portability of a given file

571

"""checks style and portability of a given file

572

573

:f: filepath

573

:f: filepath

574

:logfunc: function used to report error

574

:logfunc: function used to report error

575

logfunc(filename, linenumber, linecontent, errormessage)

575

logfunc(filename, linenumber, linecontent, errormessage)

576

:maxerr: number of error to display before aborting.

576

:maxerr: number of error to display before aborting.

577

Set to false (default) to report all errors

577

Set to false (default) to report all errors

578

579

return True if no error is found, False otherwise.

579

return True if no error is found, False otherwise.

580

"""

580

"""

581

blamecache = None

581

blamecache = None

582

result = True

582

result = True

583

584

try:

584

try:

585

with opentext(f) as fp:

585

with opentext(f) as fp:

586

try:

586

try:

587

pre = post = fp.read()

587

pre = post = fp.read()

588

except UnicodeDecodeError as e:

588

except UnicodeDecodeError as e:

589

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

589

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

590

return result

590

return result

591

except IOError as e:

591

except IOError as e:

592

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

592

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

593

return result

593

return result

594

595

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

595

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

596

post = pre # discard filtering result of previous check

596

post = pre # discard filtering result of previous check

597

if debug:

597

if debug:

598

print(name, f)

598

print(name, f)

599

fc = 0

599

fc = 0

600

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

600

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

601

if debug:

601

if debug:

602

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

602

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

603

name, match, f))

603

name, match, f))

604

continue

604

continue

605

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

605

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

606

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

606

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

607

# no- check- code

607

# no- check- code

608

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

608

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

609

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

609

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

610

# spelling, we write it with the expected spelling from

610

# spelling, we write it with the expected spelling from

611

# tests/test-check-code.t

611

# tests/test-check-code.t

612

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

612

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

613

return "Skip" # skip checking this file

613

return "Skip" # skip checking this file

614

for p, r in filters:

614

for p, r in filters:

615

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

615

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

616

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

616

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

617

if warnings:

617

if warnings:

618

pats = pats[0] + pats[1]

618

pats = pats[0] + pats[1]

619

else:

619

else:

620

pats = pats[0]

620

pats = pats[0]

621

# print post # uncomment to show filtered version

621

# print post # uncomment to show filtered version

622

623

if debug:

623

if debug:

624

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

624

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

625

626

prelines = None

626

prelines = None

627

errors = []

627

errors = []

628

for i, pat in enumerate(pats):

628

for i, pat in enumerate(pats):

629

if len(pat) == 3:

629

if len(pat) == 3:

630

p, msg, ignore = pat

630

p, msg, ignore = pat

631

else:

631

else:

632

p, msg = pat

632

p, msg = pat

633

ignore = None

633

ignore = None

634

if i >= nerrs:

634

if i >= nerrs:

635

msg = "warning: " + msg

635

msg = "warning: " + msg

636

637

pos = 0

637

pos = 0

638

n = 0

638

n = 0

639

for m in p.finditer(post):

639

for m in p.finditer(post):

640

if prelines is None:

640

if prelines is None:

641

prelines = pre.splitlines()

641

prelines = pre.splitlines()

642

postlines = post.splitlines(True)

642

postlines = post.splitlines(True)

643

644

start = m.start()

644

start = m.start()

645

while n < len(postlines):

645

while n < len(postlines):

646

step = len(postlines[n])

646

step = len(postlines[n])

647

if pos + step > start:

647

if pos + step > start:

648

break

648

break

649

pos += step

649

pos += step

650

n += 1

650

n += 1

651

l = prelines[n]

651

l = prelines[n]

652

653

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

653

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

654

if debug:

654

if debug:

655

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

655

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

656

name, f, n))

656

name, f, n))

657

continue

657

continue

658

bd = ""

658

bd = ""

659

if blame:

659

if blame:

660

bd = 'working directory'

660

bd = 'working directory'

661

if not blamecache:

661

if not blamecache:

662

blamecache = getblame(f)

662

blamecache = getblame(f)

663

if n < len(blamecache):

663

if n < len(blamecache):

664

bl, bu, br = blamecache[n]

664

bl, bu, br = blamecache[n]

665

if bl == l:

665

if bl == l:

666

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

666

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

667

668

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

668

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

669

result = False

669

result = False

670

671

errors.sort()

671

errors.sort()

672

for e in errors:

672

for e in errors:

673

logfunc(*e)

673

logfunc(*e)

674

fc += 1

674

fc += 1

675

if maxerr and fc >= maxerr:

675

if maxerr and fc >= maxerr:

676

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

676

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

677

break

677

break

678

679

return result

679

return result

680

681

def main():

681

def main():

682

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

682

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

683

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

683

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

684

help="include warning-level checks")

684

help="include warning-level checks")

685

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

685

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

686

help="max warnings per file")

686

help="max warnings per file")

687

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

687

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

688

help="use annotate to generate blame info")

688

help="use annotate to generate blame info")

689

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

689

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

690

help="show debug information")

690

help="show debug information")

691

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

691

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

692

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

692

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

693

694

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

694

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

695

lineno=True)

695

lineno=True)

696

(options, args) = parser.parse_args()

696

(options, args) = parser.parse_args()

697

698

if len(args) == 0:

698

if len(args) == 0:

699

check = glob.glob("*")

699

check = glob.glob("*")

700

elif args == ['-']:

700

elif args == ['-']:

701

# read file list from stdin

701

# read file list from stdin

702

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

702

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

703

else:

703

else:

704

check = args

704

check = args

705

706

_preparepats()

706

_preparepats()

707

708

ret = 0

708

ret = 0

709

for f in check:

709

for f in check:

710

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

710

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

711

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

711

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

712

lineno=options.lineno):

712

lineno=options.lineno):

713

ret = 1

713

ret = 1

714

return ret

714

return ret

715

716

if __name__ == "__main__":

716

if __name__ == "__main__":

717

sys.exit(main())

717

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