upstream/mercurial-mirror Commit - r32696:0c09afdf

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

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

146

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

147

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

147

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

148

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

148

],

149

],

149

# warnings

150

# warnings

150

[

151

[

151

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

152

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

152

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

153

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

153

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

154

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

154

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

155

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

155

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

156

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

156

]

157

]

157

]

158

]

158

159

testfilters = [

160

testfilters = [

160

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

161

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

161

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

162

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

162

]

163

]

163

164

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

165

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

165

uprefix = r"^ \$ "

166

uprefix = r"^ \$ "

166

utestpats = [

167

utestpats = [

167

[

168

[

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

"explicit exit code checks unnecessary"),

175

"explicit exit code checks unnecessary"),

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

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

181

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

182

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

182

winglobmsg),

183

winglobmsg),

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

209

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

209

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

210

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

210

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

211

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

211

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

212

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

212

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

213

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

213

],

214

],

214

# warnings

215

# warnings

215

[

216

[

216

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

217

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

217

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

218

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

218

]

219

]

219

]

220

]

220

221

for i in [0, 1]:

222

for i in [0, 1]:

222

for tp in testpats[i]:

223

for tp in testpats[i]:

223

p = tp[0]

224

p = tp[0]

224

m = tp[1]

225

m = tp[1]

225

if p.startswith(r'^'):

226

if p.startswith(r'^'):

226

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

227

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

227

else:

228

else:

228

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

229

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

229

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

230

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

230

231

utestfilters = [

232

utestfilters = [

232

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

233

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

233

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

234

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

234

]

235

]

235

236

pypats = [

237

pypats = [

237

[

238

[

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

'dict-from-generator'),

246

'dict-from-generator'),

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

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

256

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

257

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

257

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

258

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

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

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

262

"don't use camelcase in identifiers"),

263

"don't use camelcase in identifiers"),

263

264

264

"linebreak after :"),

265

"linebreak after :"),

265

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

266

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

266

r'#.*old-style'),

267

r'#.*old-style'),

267

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

268

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

268

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

269

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

269

r'#.*old-style'),

270

r'#.*old-style'),

270

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

271

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

271

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

272

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

272

"Python keyword is not a function"),

273

"Python keyword is not a function"),

273

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

274

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

274

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

275

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

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

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

280

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

281

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

281

"gratuitous whitespace after Python keyword"),

282

"gratuitous whitespace after Python keyword"),

282

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

283

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

283

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

284

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

284

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

285

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

285

"missing whitespace around operator"),

286

"missing whitespace around operator"),

286

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

287

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

287

"missing whitespace around operator"),

288

"missing whitespace around operator"),

288

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

289

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

289

"missing whitespace around operator"),

290

"missing whitespace around operator"),

290

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

291

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

291

"wrong whitespace around ="),

292

"wrong whitespace around ="),

292

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

293

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

293

"no whitespace around = for named parameters"),

294

"no whitespace around = for named parameters"),

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

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

306

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

306

"use opener.read() instead"),

307

"use opener.read() instead"),

307

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

308

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

308

"use opener.write() instead"),

309

"use opener.write() instead"),

309

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

310

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

310

"use util.readfile() instead"),

311

"use util.readfile() instead"),

311

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

312

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

312

"use util.writefile() instead"),

313

"use util.writefile() instead"),

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

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

337

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

337

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

338

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

338

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

339

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

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

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

344

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

344

"use mercurial.policy.importmod instead"),

345

"use mercurial.policy.importmod instead"),

345

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

346

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

346

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

347

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

347

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

348

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

348

349

# rules depending on implementation of repquote()

350

# rules depending on implementation of repquote()

350

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

351

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

351

'string join across lines with no space'),

352

'string join across lines with no space'),

352

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

353

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

353

[ \t\n#]*

354

[ \t\n#]*

354

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

355

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

355

# contains translatable message)

356

# contains translatable message)

356

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

357

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

357

(?# sequence consisting of below might precede translatable message

358

(?# sequence consisting of below might precede translatable message

358

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

359

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

359

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

360

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

360

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

361

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

361

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

362

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

362

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

363

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

363

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

364

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

364

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

365

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

365

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

366

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

366

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

367

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

367

],

368

],

368

# warnings

369

# warnings

369

[

370

[

370

# rules depending on implementation of repquote()

371

# rules depending on implementation of repquote()

371

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

372

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

372

]

373

]

373

]

374

]

374

375

pyfilters = [

376

pyfilters = [

376

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

377

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

377

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

378

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

378

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

379

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

379

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

380

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

380

]

381

]

381

382

# extension non-filter patterns

383

# extension non-filter patterns

383

pyextnfpats = [

384

pyextnfpats = [

384

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

385

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

385

# warnings

386

# warnings

386

[],

387

[],

387

]

388

]

388

389

txtfilters = []

390

txtfilters = []

390

391

txtpats = [

392

txtpats = [

392

[

393

[

393

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

394

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

394

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

395

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

395

],

396

],

396

[]

397

[]

397

]

398

]

398

399

cpats = [

400

cpats = [

400

[

401

[

401

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

402

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

402

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

403

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

403

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

404

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

404

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

405

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

405

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

406

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

406

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

407

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

407

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

408

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

408

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

409

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

409

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

410

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

410

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

411

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

411

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

412

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

412

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

413

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

413

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

414

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

414

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

415

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

415

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

416

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

416

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

417

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

417

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

418

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

418

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

419

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

419

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

420

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

420

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

421

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

421

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

422

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

422

423

# rules depending on implementation of repquote()

424

# rules depending on implementation of repquote()

424

],

425

],

425

# warnings

426

# warnings

426

[

427

[

427

# rules depending on implementation of repquote()

428

# rules depending on implementation of repquote()

428

]

429

]

429

]

430

]

430

431

cfilters = [

432

cfilters = [

432

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

433

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

433

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

434

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

434

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

435

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

435

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

436

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

436

]

437

]

437

438

inutilpats = [

439

inutilpats = [

439

[

440

[

440

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

441

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

441

],

442

],

442

# warnings

443

# warnings

443

[]

444

[]

444

]

445

]

445

446

inrevlogpats = [

447

inrevlogpats = [

447

[

448

[

448

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

449

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

449

],

450

],

450

# warnings

451

# warnings

451

[]

452

[]

452

]

453

]

453

454

webtemplatefilters = []

455

webtemplatefilters = []

455

456

webtemplatepats = [

457

webtemplatepats = [

457

[],

458

[],

458

[

459

[

459

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

460

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

460

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

461

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

461

]

462

]

462

]

463

]

463

464

allfilesfilters = []

465

allfilesfilters = []

465

466

allfilespats = [

467

allfilespats = [

467

[

468

[

468

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

469

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

469

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

470

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

470

(r'mercurial@selenic\.com',

471

(r'mercurial@selenic\.com',

471

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

472

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

472

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

473

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

473

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

474

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

474

],

475

],

475

# warnings

476

# warnings

476

[],

477

[],

477

]

478

]

478

479

py3pats = [

480

py3pats = [

480

[

481

[

481

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

482

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

482

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

483

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

483

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

484

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

484

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

485

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

485

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

486

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

486

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

487

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

487

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

488

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

488

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

489

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

489

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

490

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

490

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

491

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

491

],

492

],

492

# warnings

493

# warnings

493

[],

494

[],

494

]

495

]

495

496

checks = [

497

checks = [

497

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

498

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

498

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

499

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

499

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

500

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

500

'', pyfilters, py3pats),

501

'', pyfilters, py3pats),

501

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

502

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

502

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

503

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

503

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

504

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

504

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

505

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

505

pyfilters, inrevlogpats),

506

pyfilters, inrevlogpats),

506

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

507

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

507

inutilpats),

508

inutilpats),

508

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

509

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

509

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

510

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

510

webtemplatefilters, webtemplatepats),

511

webtemplatefilters, webtemplatepats),

511

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

512

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

512

allfilesfilters, allfilespats),

513

allfilesfilters, allfilespats),

513

]

514

]

514

515

def _preparepats():

516

def _preparepats():

516

for c in checks:

517

for c in checks:

517

failandwarn = c[-1]

518

failandwarn = c[-1]

518

for pats in failandwarn:

519

for pats in failandwarn:

519

for i, pseq in enumerate(pats):

520

for i, pseq in enumerate(pats):

520

# fix-up regexes for multi-line searches

521

# fix-up regexes for multi-line searches

521

p = pseq[0]

522

p = pseq[0]

522

# \s doesn't match \n

523

# \s doesn't match \n

523

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

524

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

524

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

525

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

525

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

526

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

526

527

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

528

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

528

filters = c[3]

529

filters = c[3]

529

for i, flt in enumerate(filters):

530

for i, flt in enumerate(filters):

530

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

531

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

531

532

class norepeatlogger(object):

533

class norepeatlogger(object):

533

def __init__(self):

534

def __init__(self):

534

self._lastseen = None

535

self._lastseen = None

535

536

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

537

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

537

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

538

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

538

539

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

540

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

540

of multiple errors.

541

of multiple errors.

541

542

:fname: filename

543

:fname: filename

543

:lineno: line number

544

:lineno: line number

544

:line: actual content of the line

545

:line: actual content of the line

545

:msg: error message

546

:msg: error message

546

"""

547

"""

547

msgid = fname, lineno, line

548

msgid = fname, lineno, line

548

if msgid != self._lastseen:

549

if msgid != self._lastseen:

549

if blame:

550

if blame:

550

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

551

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

551

else:

552

else:

552

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

553

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

553

print(" > %s" % line)

554

print(" > %s" % line)

554

self._lastseen = msgid

555

self._lastseen = msgid

555

print(" " + msg)

556

print(" " + msg)

556

557

_defaultlogger = norepeatlogger()

558

_defaultlogger = norepeatlogger()

558

559

def getblame(f):

560

def getblame(f):

560

lines = []

561

lines = []

561

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

562

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

562

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

563

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

563

user, rev = start.split()

564

user, rev = start.split()

564

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

565

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

565

return lines

566

return lines

566

567

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

568

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

568

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

569

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

569

"""checks style and portability of a given file

570

"""checks style and portability of a given file

570

571

:f: filepath

572

:f: filepath

572

:logfunc: function used to report error

573

:logfunc: function used to report error

573

logfunc(filename, linenumber, linecontent, errormessage)

574

logfunc(filename, linenumber, linecontent, errormessage)

574

:maxerr: number of error to display before aborting.

575

:maxerr: number of error to display before aborting.

575

Set to false (default) to report all errors

576

Set to false (default) to report all errors

576

577

return True if no error is found, False otherwise.

578

return True if no error is found, False otherwise.

578

"""

579

"""

579

blamecache = None

580

blamecache = None

580

result = True

581

result = True

581

582

try:

583

try:

583

with opentext(f) as fp:

584

with opentext(f) as fp:

584

try:

585

try:

585

pre = post = fp.read()

586

pre = post = fp.read()

586

except UnicodeDecodeError as e:

587

except UnicodeDecodeError as e:

587

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

588

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

588

return result

589

return result

589

except IOError as e:

590

except IOError as e:

590

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

591

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

591

return result

592

return result

592

593

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

594

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

594

post = pre # discard filtering result of previous check

595

post = pre # discard filtering result of previous check

595

if debug:

596

if debug:

596

print(name, f)

597

print(name, f)

597

fc = 0

598

fc = 0

598

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

599

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

599

if debug:

600

if debug:

600

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

601

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

601

name, match, f))

602

name, match, f))

602

continue

603

continue

603

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

604

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

604

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

605

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

605

# no- check- code

606

# no- check- code

606

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

607

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

607

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

608

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

608

# spelling, we write it with the expected spelling from

609

# spelling, we write it with the expected spelling from

609

# tests/test-check-code.t

610

# tests/test-check-code.t

610

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

611

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

611

return "Skip" # skip checking this file

612

return "Skip" # skip checking this file

612

for p, r in filters:

613

for p, r in filters:

613

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

614

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

614

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

615

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

615

if warnings:

616

if warnings:

616

pats = pats[0] + pats[1]

617

pats = pats[0] + pats[1]

617

else:

618

else:

618

pats = pats[0]

619

pats = pats[0]

619

# print post # uncomment to show filtered version

620

# print post # uncomment to show filtered version

620

621

if debug:

622

if debug:

622

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

623

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

623

624

prelines = None

625

prelines = None

625

errors = []

626

errors = []

626

for i, pat in enumerate(pats):

627

for i, pat in enumerate(pats):

627

if len(pat) == 3:

628

if len(pat) == 3:

628

p, msg, ignore = pat

629

p, msg, ignore = pat

629

else:

630

else:

630

p, msg = pat

631

p, msg = pat

631

ignore = None

632

ignore = None

632

if i >= nerrs:

633

if i >= nerrs:

633

msg = "warning: " + msg

634

msg = "warning: " + msg

634

635

pos = 0

636

pos = 0

636

n = 0

637

n = 0

637

for m in p.finditer(post):

638

for m in p.finditer(post):

638

if prelines is None:

639

if prelines is None:

639

prelines = pre.splitlines()

640

prelines = pre.splitlines()

640

postlines = post.splitlines(True)

641

postlines = post.splitlines(True)

641

642

start = m.start()

643

start = m.start()

643

while n < len(postlines):

644

while n < len(postlines):

644

step = len(postlines[n])

645

step = len(postlines[n])

645

if pos + step > start:

646

if pos + step > start:

646

break

647

break

647

pos += step

648

pos += step

648

n += 1

649

n += 1

649

l = prelines[n]

650

l = prelines[n]

650

651

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

652

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

652

if debug:

653

if debug:

653

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

654

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

654

name, f, n))

655

name, f, n))

655

continue

656

continue

656

bd = ""

657

bd = ""

657

if blame:

658

if blame:

658

bd = 'working directory'

659

bd = 'working directory'

659

if not blamecache:

660

if not blamecache:

660

blamecache = getblame(f)

661

blamecache = getblame(f)

661

if n < len(blamecache):

662

if n < len(blamecache):

662

bl, bu, br = blamecache[n]

663

bl, bu, br = blamecache[n]

663

if bl == l:

664

if bl == l:

664

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

665

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

665

666

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

667

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

667

result = False

668

result = False

668

669

errors.sort()

670

errors.sort()

670

for e in errors:

671

for e in errors:

671

logfunc(*e)

672

logfunc(*e)

672

fc += 1

673

fc += 1

673

if maxerr and fc >= maxerr:

674

if maxerr and fc >= maxerr:

674

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

675

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

675

break

676

break

676

677

return result

678

return result

678

679

def main():

680

def main():

680

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

681

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

681

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

682

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

682

help="include warning-level checks")

683

help="include warning-level checks")

683

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

684

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

684

help="max warnings per file")

685

help="max warnings per file")

685

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

686

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

686

help="use annotate to generate blame info")

687

help="use annotate to generate blame info")

687

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

688

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

688

help="show debug information")

689

help="show debug information")

689

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

690

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

690

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

691

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

691

692

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

693

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

693

lineno=True)

694

lineno=True)

694

(options, args) = parser.parse_args()

695

(options, args) = parser.parse_args()

695

696

if len(args) == 0:

697

if len(args) == 0:

697

check = glob.glob("*")

698

check = glob.glob("*")

698

elif args == ['-']:

699

elif args == ['-']:

699

# read file list from stdin

700

# read file list from stdin

700

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

701

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

701

else:

702

else:

702

check = args

703

check = args

703

704

_preparepats()

705

_preparepats()

705

706

ret = 0

707

ret = 0

707

for f in check:

708

for f in check:

708

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

709

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

709

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

710

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

710

lineno=options.lineno):

711

lineno=options.lineno):

711

ret = 1

712

ret = 1

712

return ret

713

return ret

713

714

if __name__ == "__main__":

715

if __name__ == "__main__":

715

sys.exit(main())

716

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'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())