upstream/mercurial-mirror Commit - r36182:c38e9248

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'(^|\|\s*)e?grep .*\\S', "don't use \\S in regular expression"),

122

(r'(^|\|\s*)e?grep .*\\S', "don't use \\S in regular expression"),

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

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

146

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

147

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

147

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

148

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

148

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

149

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

149

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

150

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

150

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

151

(r'find.*-printf',

151

(r'find.*-printf',

152

"don't use 'find -printf', it doesn't exist on BSD find(1)"),

152

"don't use 'find -printf', it doesn't exist on BSD find(1)"),

153

(r'\$RANDOM ', "don't use bash-only $RANDOM to generate random values"),

153

],

154

],

154

# warnings

155

# warnings

155

[

156

[

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

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

160

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

161

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

161

]

162

]

162

]

163

]

163

164

testfilters = [

165

testfilters = [

165

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

166

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

166

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

167

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

167

]

168

]

168

169

uprefix = r"^ \$ "

170

uprefix = r"^ \$ "

170

utestpats = [

171

utestpats = [

171

[

172

[

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

"explicit exit code checks unnecessary"),

179

"explicit exit code checks unnecessary"),

179

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

180

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

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

(r'^ (cat|find): .*: \$ENOENT\$',

189

(r'^ (cat|find): .*: \$ENOENT\$',

189

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

190

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

190

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

191

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

191

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

192

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

192

(r' readlink ', 'use readlink.py instead of readlink'),

193

(r' readlink ', 'use readlink.py instead of readlink'),

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

],

205

],

205

# warnings

206

# warnings

206

[

207

[

207

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

208

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

208

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

209

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

209

]

210

]

210

]

211

]

211

212

# transform plain test rules to unified test's

213

# transform plain test rules to unified test's

213

for i in [0, 1]:

214

for i in [0, 1]:

214

for tp in testpats[i]:

215

for tp in testpats[i]:

215

p = tp[0]

216

p = tp[0]

216

m = tp[1]

217

m = tp[1]

217

if p.startswith(r'^'):

218

if p.startswith(r'^'):

218

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

219

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

219

else:

220

else:

220

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

221

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

221

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

222

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

222

223

# don't transform the following rules:

224

# don't transform the following rules:

224

# " > \t" and " \t" should be allowed in unified tests

225

# " > \t" and " \t" should be allowed in unified tests

225

testpats[0].append((r'^( *)\t', "don't use tabs to indent"))

226

testpats[0].append((r'^( *)\t', "don't use tabs to indent"))

226

utestpats[0].append((r'^( ?)\t', "don't use tabs to indent"))

227

utestpats[0].append((r'^( ?)\t', "don't use tabs to indent"))

227

228

utestfilters = [

229

utestfilters = [

229

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

230

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

230

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

231

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

231

]

232

]

232

233

pypats = [

234

pypats = [

234

[

235

[

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

'dict-from-generator'),

243

'dict-from-generator'),

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

((

254

((

254

# a line ending with a colon, potentially with trailing comments

255

# a line ending with a colon, potentially with trailing comments

255

r':([ \t]*#[^\n]*)?\n'

256

r':([ \t]*#[^\n]*)?\n'

256

# one that is not a pass and not only a comment

257

# one that is not a pass and not only a comment

257

r'(?P<indent>[ \t]+)[^#][^\n]+\n'

258

r'(?P<indent>[ \t]+)[^#][^\n]+\n'

258

# more lines at the same indent level

259

# more lines at the same indent level

259

r'((?P=indent)[^\n]+\n)*'

260

r'((?P=indent)[^\n]+\n)*'

260

# a pass at the same indent level, which is bogus

261

# a pass at the same indent level, which is bogus

261

r'(?P=indent)pass[ \t\n#]'

262

r'(?P=indent)pass[ \t\n#]'

262

), 'omit superfluous pass'),

263

), 'omit superfluous pass'),

263

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

264

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

264

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

265

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

265

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

266

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

266

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

267

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

267

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

268

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

268

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

269

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

269

"don't use camelcase in identifiers", r'#.*camelcase-required'),

270

"don't use camelcase in identifiers", r'#.*camelcase-required'),

270

271

271

"linebreak after :"),

272

"linebreak after :"),

272

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

273

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

273

r'#.*old-style'),

274

r'#.*old-style'),

274

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

275

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

275

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

276

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

276

r'#.*old-style'),

277

r'#.*old-style'),

277

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

278

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

278

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

279

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

279

"Python keyword is not a function"),

280

"Python keyword is not a function"),

280

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

281

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

281

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

282

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

282

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

283

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

283

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

284

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

284

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

285

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

285

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

286

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

286

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

287

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

287

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

288

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

288

"gratuitous whitespace after Python keyword"),

289

"gratuitous whitespace after Python keyword"),

289

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

290

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

290

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

291

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

291

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

292

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

292

"missing whitespace around operator"),

293

"missing whitespace around operator"),

293

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

294

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

294

"missing whitespace around operator"),

295

"missing whitespace around operator"),

295

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

296

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

296

"missing whitespace around operator"),

297

"missing whitespace around operator"),

297

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

298

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

298

"wrong whitespace around ="),

299

"wrong whitespace around ="),

299

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

300

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

300

"no whitespace around = for named parameters"),

301

"no whitespace around = for named parameters"),

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

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

306

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

306

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

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

"use opener.read() instead"),

315

"use opener.read() instead"),

315

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

316

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

316

"use opener.write() instead"),

317

"use opener.write() instead"),

317

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

318

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

318

"use util.readfile() instead"),

319

"use util.readfile() instead"),

319

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

320

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

320

"use util.writefile() instead"),

321

"use util.writefile() instead"),

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

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

337

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

337

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

338

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

338

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

339

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

339

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

340

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

340

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

341

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

341

(r'^import atexit', "don't use atexit, use ui.atexit"),

342

(r'^import atexit', "don't use atexit, use ui.atexit"),

342

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

343

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

343

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

344

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

344

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

345

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

345

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

346

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

346

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

347

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

347

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

348

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

348

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

349

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

349

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

350

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

350

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

351

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

351

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

352

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

352

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

353

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

353

"use mercurial.policy.importmod instead"),

354

"use mercurial.policy.importmod instead"),

354

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

355

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

355

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

356

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

356

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

357

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

357

(r'platform\.system', "don't use platform.system(), use pycompat"),

358

(r'platform\.system', "don't use platform.system(), use pycompat"),

358

359

# rules depending on implementation of repquote()

360

# rules depending on implementation of repquote()

360

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

361

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

361

'string join across lines with no space'),

362

'string join across lines with no space'),

362

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

363

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

363

[ \t\n#]*

364

[ \t\n#]*

364

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

365

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

365

# contains translatable message)

366

# contains translatable message)

366

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

367

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

367

(?# sequence consisting of below might precede translatable message

368

(?# sequence consisting of below might precede translatable message

368

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

369

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

369

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

370

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

370

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

371

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

371

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

372

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

372

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

373

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

373

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

374

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

374

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

375

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

375

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

376

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

376

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

377

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

377

],

378

],

378

# warnings

379

# warnings

379

[

380

[

380

# rules depending on implementation of repquote()

381

# rules depending on implementation of repquote()

381

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

382

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

382

]

383

]

383

]

384

]

384

385

pyfilters = [

386

pyfilters = [

386

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

387

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

387

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

388

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

388

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

389

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

389

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

390

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

390

]

391

]

391

392

# non-filter patterns

393

# non-filter patterns

393

pynfpats = [

394

pynfpats = [

394

[

395

[

395

(r'pycompat\.osname\s*[=!]=\s*[\'"]nt[\'"]', "use pycompat.iswindows"),

396

(r'pycompat\.osname\s*[=!]=\s*[\'"]nt[\'"]', "use pycompat.iswindows"),

396

(r'pycompat\.osname\s*[=!]=\s*[\'"]posix[\'"]', "use pycompat.isposix"),

397

(r'pycompat\.osname\s*[=!]=\s*[\'"]posix[\'"]', "use pycompat.isposix"),

397

(r'pycompat\.sysplatform\s*[!=]=\s*[\'"]darwin[\'"]',

398

(r'pycompat\.sysplatform\s*[!=]=\s*[\'"]darwin[\'"]',

398

"use pycompat.isdarwin"),

399

"use pycompat.isdarwin"),

399

],

400

],

400

# warnings

401

# warnings

401

[],

402

[],

402

]

403

]

403

404

# extension non-filter patterns

405

# extension non-filter patterns

405

pyextnfpats = [

406

pyextnfpats = [

406

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

407

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

407

# warnings

408

# warnings

408

[],

409

[],

409

]

410

]

410

411

txtfilters = []

412

txtfilters = []

412

413

txtpats = [

414

txtpats = [

414

[

415

[

415

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

416

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

416

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

417

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

417

],

418

],

418

[]

419

[]

419

]

420

]

420

421

cpats = [

422

cpats = [

422

[

423

[

423

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

424

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

424

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

425

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

425

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

426

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

426

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

427

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

427

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

428

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

428

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

429

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

429

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

430

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

430

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

431

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

431

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

432

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

432

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

433

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

433

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

434

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

434

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

435

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

435

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

436

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

436

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

437

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

437

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

438

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

438

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

439

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

439

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

440

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

440

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

441

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

441

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

442

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

442

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

443

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

443

444

# rules depending on implementation of repquote()

445

# rules depending on implementation of repquote()

445

],

446

],

446

# warnings

447

# warnings

447

[

448

[

448

# rules depending on implementation of repquote()

449

# rules depending on implementation of repquote()

449

]

450

]

450

]

451

]

451

452

cfilters = [

453

cfilters = [

453

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

454

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

454

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

455

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

455

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

456

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

456

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

457

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

457

]

458

]

458

459

inutilpats = [

460

inutilpats = [

460

[

461

[

461

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

462

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

462

],

463

],

463

# warnings

464

# warnings

464

[]

465

[]

465

]

466

]

466

467

inrevlogpats = [

468

inrevlogpats = [

468

[

469

[

469

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

470

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

470

],

471

],

471

# warnings

472

# warnings

472

[]

473

[]

473

]

474

]

474

475

webtemplatefilters = []

476

webtemplatefilters = []

476

477

webtemplatepats = [

478

webtemplatepats = [

478

[],

479

[],

479

[

480

[

480

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

481

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

481

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

482

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

482

]

483

]

483

]

484

]

484

485

allfilesfilters = []

486

allfilesfilters = []

486

487

allfilespats = [

488

allfilespats = [

488

[

489

[

489

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

490

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

490

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

491

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

491

(r'mercurial@selenic\.com',

492

(r'mercurial@selenic\.com',

492

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

493

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

493

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

494

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

494

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

495

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

495

],

496

],

496

# warnings

497

# warnings

497

[],

498

[],

498

]

499

]

499

500

py3pats = [

501

py3pats = [

501

[

502

[

502

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

503

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

503

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

504

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

504

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

505

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

505

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

506

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

506

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

507

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

507

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

508

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

508

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

509

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

509

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

510

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

510

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

511

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

511

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

512

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

512

],

513

],

513

# warnings

514

# warnings

514

[],

515

[],

515

]

516

]

516

517

checks = [

518

checks = [

518

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

519

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

519

('python', r'.*\.(py|cgi)$', r'^#!.*python', [], pynfpats),

520

('python', r'.*\.(py|cgi)$', r'^#!.*python', [], pynfpats),

520

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

521

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

521

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

522

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

522

'', pyfilters, py3pats),

523

'', pyfilters, py3pats),

523

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

524

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

524

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

525

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

525

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

526

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

526

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

527

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

527

pyfilters, inrevlogpats),

528

pyfilters, inrevlogpats),

528

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

529

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

529

inutilpats),

530

inutilpats),

530

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

531

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

531

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

532

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

532

webtemplatefilters, webtemplatepats),

533

webtemplatefilters, webtemplatepats),

533

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

534

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

534

allfilesfilters, allfilespats),

535

allfilesfilters, allfilespats),

535

]

536

]

536

537

def _preparepats():

538

def _preparepats():

538

for c in checks:

539

for c in checks:

539

failandwarn = c[-1]

540

failandwarn = c[-1]

540

for pats in failandwarn:

541

for pats in failandwarn:

541

for i, pseq in enumerate(pats):

542

for i, pseq in enumerate(pats):

542

# fix-up regexes for multi-line searches

543

# fix-up regexes for multi-line searches

543

p = pseq[0]

544

p = pseq[0]

544

# \s doesn't match \n

545

# \s doesn't match \n

545

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

546

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

546

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

547

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

547

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

548

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

548

549

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

550

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

550

filters = c[3]

551

filters = c[3]

551

for i, flt in enumerate(filters):

552

for i, flt in enumerate(filters):

552

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

553

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

553

554

class norepeatlogger(object):

555

class norepeatlogger(object):

555

def __init__(self):

556

def __init__(self):

556

self._lastseen = None

557

self._lastseen = None

557

558

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

559

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

559

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

560

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

560

561

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

562

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

562

of multiple errors.

563

of multiple errors.

563

564

:fname: filename

565

:fname: filename

565

:lineno: line number

566

:lineno: line number

566

:line: actual content of the line

567

:line: actual content of the line

567

:msg: error message

568

:msg: error message

568

"""

569

"""

569

msgid = fname, lineno, line

570

msgid = fname, lineno, line

570

if msgid != self._lastseen:

571

if msgid != self._lastseen:

571

if blame:

572

if blame:

572

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

573

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

573

else:

574

else:

574

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

575

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

575

print(" > %s" % line)

576

print(" > %s" % line)

576

self._lastseen = msgid

577

self._lastseen = msgid

577

print(" " + msg)

578

print(" " + msg)

578

579

_defaultlogger = norepeatlogger()

580

_defaultlogger = norepeatlogger()

580

581

def getblame(f):

582

def getblame(f):

582

lines = []

583

lines = []

583

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

584

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

584

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

585

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

585

user, rev = start.split()

586

user, rev = start.split()

586

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

587

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

587

return lines

588

return lines

588

589

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

590

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

590

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

591

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

591

"""checks style and portability of a given file

592

"""checks style and portability of a given file

592

593

:f: filepath

594

:f: filepath

594

:logfunc: function used to report error

595

:logfunc: function used to report error

595

logfunc(filename, linenumber, linecontent, errormessage)

596

logfunc(filename, linenumber, linecontent, errormessage)

596

:maxerr: number of error to display before aborting.

597

:maxerr: number of error to display before aborting.

597

Set to false (default) to report all errors

598

Set to false (default) to report all errors

598

599

return True if no error is found, False otherwise.

600

return True if no error is found, False otherwise.

600

"""

601

"""

601

blamecache = None

602

blamecache = None

602

result = True

603

result = True

603

604

try:

605

try:

605

with opentext(f) as fp:

606

with opentext(f) as fp:

606

try:

607

try:

607

pre = post = fp.read()

608

pre = post = fp.read()

608

except UnicodeDecodeError as e:

609

except UnicodeDecodeError as e:

609

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

610

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

610

return result

611

return result

611

except IOError as e:

612

except IOError as e:

612

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

613

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

613

return result

614

return result

614

615

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

616

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

616

post = pre # discard filtering result of previous check

617

post = pre # discard filtering result of previous check

617

if debug:

618

if debug:

618

print(name, f)

619

print(name, f)

619

fc = 0

620

fc = 0

620

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

621

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

621

if debug:

622

if debug:

622

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

623

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

623

name, match, f))

624

name, match, f))

624

continue

625

continue

625

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

626

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

626

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

627

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

627

# no- check- code

628

# no- check- code

628

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

629

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

629

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

630

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

630

# spelling, we write it with the expected spelling from

631

# spelling, we write it with the expected spelling from

631

# tests/test-check-code.t

632

# tests/test-check-code.t

632

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

633

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

633

return "Skip" # skip checking this file

634

return "Skip" # skip checking this file

634

for p, r in filters:

635

for p, r in filters:

635

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

636

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

636

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

637

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

637

if warnings:

638

if warnings:

638

pats = pats[0] + pats[1]

639

pats = pats[0] + pats[1]

639

else:

640

else:

640

pats = pats[0]

641

pats = pats[0]

641

# print post # uncomment to show filtered version

642

# print post # uncomment to show filtered version

642

643

if debug:

644

if debug:

644

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

645

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

645

646

prelines = None

647

prelines = None

647

errors = []

648

errors = []

648

for i, pat in enumerate(pats):

649

for i, pat in enumerate(pats):

649

if len(pat) == 3:

650

if len(pat) == 3:

650

p, msg, ignore = pat

651

p, msg, ignore = pat

651

else:

652

else:

652

p, msg = pat

653

p, msg = pat

653

ignore = None

654

ignore = None

654

if i >= nerrs:

655

if i >= nerrs:

655

msg = "warning: " + msg

656

msg = "warning: " + msg

656

657

pos = 0

658

pos = 0

658

n = 0

659

n = 0

659

for m in p.finditer(post):

660

for m in p.finditer(post):

660

if prelines is None:

661

if prelines is None:

661

prelines = pre.splitlines()

662

prelines = pre.splitlines()

662

postlines = post.splitlines(True)

663

postlines = post.splitlines(True)

663

664

start = m.start()

665

start = m.start()

665

while n < len(postlines):

666

while n < len(postlines):

666

step = len(postlines[n])

667

step = len(postlines[n])

667

if pos + step > start:

668

if pos + step > start:

668

break

669

break

669

pos += step

670

pos += step

670

n += 1

671

n += 1

671

l = prelines[n]

672

l = prelines[n]

672

673

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

674

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

674

if debug:

675

if debug:

675

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

676

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

676

name, f, n))

677

name, f, n))

677

continue

678

continue

678

bd = ""

679

bd = ""

679

if blame:

680

if blame:

680

bd = 'working directory'

681

bd = 'working directory'

681

if not blamecache:

682

if not blamecache:

682

blamecache = getblame(f)

683

blamecache = getblame(f)

683

if n < len(blamecache):

684

if n < len(blamecache):

684

bl, bu, br = blamecache[n]

685

bl, bu, br = blamecache[n]

685

if bl == l:

686

if bl == l:

686

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

687

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

687

688

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

689

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

689

result = False

690

result = False

690

691

errors.sort()

692

errors.sort()

692

for e in errors:

693

for e in errors:

693

logfunc(*e)

694

logfunc(*e)

694

fc += 1

695

fc += 1

695

if maxerr and fc >= maxerr:

696

if maxerr and fc >= maxerr:

696

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

697

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

697

break

698

break

698

699

return result

700

return result

700

701

def main():

702

def main():

702

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

703

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

703

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

704

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

704

help="include warning-level checks")

705

help="include warning-level checks")

705

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

706

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

706

help="max warnings per file")

707

help="max warnings per file")

707

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

708

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

708

help="use annotate to generate blame info")

709

help="use annotate to generate blame info")

709

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

710

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

710

help="show debug information")

711

help="show debug information")

711

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

712

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

712

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

713

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

713

714

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

715

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

715

lineno=True)

716

lineno=True)

716

(options, args) = parser.parse_args()

717

(options, args) = parser.parse_args()

717

718

if len(args) == 0:

719

if len(args) == 0:

719

check = glob.glob("*")

720

check = glob.glob("*")

720

elif args == ['-']:

721

elif args == ['-']:

721

# read file list from stdin

722

# read file list from stdin

722

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

723

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

723

else:

724

else:

724

check = args

725

check = args

725

726

_preparepats()

727

_preparepats()

727

728

ret = 0

729

ret = 0

729

for f in check:

730

for f in check:

730

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

731

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

731

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

732

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

732

lineno=options.lineno):

733

lineno=options.lineno):

733

ret = 1

734

ret = 1

734

return ret

735

return ret

735

736

if __name__ == "__main__":

737

if __name__ == "__main__":

737

sys.exit(main())

738

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'(^|\|\s*)e?grep .*\\S', "don't use \\S in regular expression"),
                 (r'(?<!!)/bin/', "don't use explicit paths for tools"),
                 (r'#!.*/bash', "don't use bash in shebang, use sh"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'export .*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                 (r'\bls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
                 (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
                 (r'^stop\(\)', "don't use 'stop' as a shell function name"),
                 (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
                 (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
                 (r'^alias\b.*=', "don't use alias, use a function"),
                 (r'if\s*!', "don't use '!' to negate exit status"),
                 (r'/dev/u?random', "don't use entropy, use /dev/zero"),
                 (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
                 (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
                  "put a backslash-escaped newline after sed 'i' command"),
                 (r'^diff *-\w*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
                 (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
                 (r'[\s="`\']python\s(?!bindings)', "don't use 'python', use '$PYTHON'"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'\|&', "don't use |&, use 2>&1"),
                 (r'\w =  +\w', "only one space after = allowed"),
                 (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
                 (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),
                 (r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),
                 (r'grep.* -[ABC]', "don't use grep's context flags"),
                 (r'find.*-printf',
                  "don't use 'find -printf', it doesn't exist on BSD find(1)"),
+                (r'\$RANDOM ', "don't use bash-only $RANDOM to generate random values"),
               ],
               # 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),
             ]
             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'^  [^$>].*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): .*: \$ENOENT\$',
                  'use test -f to test for file existence'),
                 (r'^  diff -[^ -]*p',
                  "don't use (external) diff with -p for portability"),
                 (r' readlink ', 'use readlink.py instead of readlink'),
                 (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 $LOCALIP)"),
               ]
             ]
             # transform plain test rules to unified test's
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%s)" % p[1:]
                     else:
                         p = r"^  [$>] .*(%s)" % p
                     utestpats[i].append((p, m) + tp[2:])
             # don't transform the following rules:
             # "  > \t" and "  \t" should be allowed in unified tests
             testpats[0].append((r'^( *)\t', "don't use tabs to indent"))
             utestpats[0].append((r'^( ?)\t', "don't use tabs to indent"))
             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 ="),
                 ((
                     # a line ending with a colon, potentially with trailing comments
                     r':([ \t]*#[^\n]*)?\n'
                     # one that is not a pass and not only a comment
                     r'(?P<indent>[ \t]+)[^#][^\n]+\n'
                     # more lines at the same indent level
                     r'((?P=indent)[^\n]+\n)*'
                     # a pass at the same indent level, which is bogus
                     r'(?P=indent)pass[ \t\n#]'
                   ), 'omit superfluous pass'),
                 (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'#.*camelcase-required'),
                 (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                  "linebreak after :"),
                 (r'class\s[^( \n]+:', "old-style class, use class foo(object)",
                  r'#.*old-style'),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)",
                  r'#.*old-style'),
                 (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                                         if k not in ('print', 'exec')),
                  "Python keyword is not a function"),
                 (r',]', "unneeded trailing ',' in list"),
             #    (r'class\s[A-Z][^\(]*\((?!Exception)',
             #     "don't capitalize non-exception classes"),
             #    (r'in range\(', "use xrange"),
             #    (r'^\s*print\s+', "avoid using print in core and extensions"),
                 (r'[\x80-\xff]', "non-ASCII character literal"),
                 (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
                 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
                  "gratuitous whitespace after Python keyword"),
                 (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
             #    (r'\s\s=', "gratuitous whitespace before ="),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
                  "missing whitespace around operator"),
                 (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
                  "wrong whitespace around ="),
                 (r'\([^()]*( =[^=]|[^<>!=]= )',
                  "no whitespace around = for named parameters"),
                 (r'raise Exception', "don't raise generic exceptions"),
                 (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                  "don't use old-style two-argument raise, use Exception(message)"),
                 (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                 (r' [=!]=\s+(True|False|None)',
                  "comparison with singleton, use 'is' or 'is not' instead"),
                 (r'^\s*(while|if) [01]:',
                  "use True/False for constant Boolean expression"),
                 (r'^\s*if False(:| +and)', 'Remove code instead of using `if False`'),
                 (r'(?:(?<!def)\s+|\()hasattr\(',
                  'hasattr(foo, bar) is broken on py2, use util.safehasattr(foo, bar) '
                  'instead', r'#.*hasattr-py3-only'),
                 (r'opener\([^)]*\).read\(',
                  "use opener.read() instead"),
                 (r'opener\([^)]*\).write\(',
                  "use opener.write() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.read\(',
                  "use util.readfile() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.write\(',
                  "use util.writefile() instead"),
                 (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'[\s\(](open|file)\([^)]*\)\.',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
                 (r'\.debug\(\_', "don't mark debug messages for translation"),
                 (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
                 (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
                 (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
                  'legacy exception syntax; use "as" instead of ","'),
                 (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                 (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
                 (r'\bdef\s+__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
                 (r'os\.path\.join\(.*, *(""|\'\')\)',
                  "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
                 (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
                 # XXX only catch mutable arguments on the first line of the definition
                 (r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'^@(\w*\.)?cachefunc', "module-level @cachefunc is risky, please avoid"),
                 (r'^import atexit', "don't use atexit, use ui.atexit"),
                 (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)"),
                 (r'platform\.system\(\)', "don't use platform.system(), use pycompat"),
                 # 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>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""", reppython),
             ]
             # non-filter patterns
             pynfpats = [
                 [
                 (r'pycompat\.osname\s*[=!]=\s*[\'"]nt[\'"]', "use pycompat.iswindows"),
                 (r'pycompat\.osname\s*[=!]=\s*[\'"]posix[\'"]', "use pycompat.isposix"),
                 (r'pycompat\.sysplatform\s*[!=]=\s*[\'"]darwin[\'"]',
                  "use pycompat.isdarwin"),
                 ],
                 # warnings
                 [],
             ]
             # extension non-filter patterns
             pyextnfpats = [
                 [(r'^"""\n?[A-Z]', "don't capitalize docstring title")],
                 # warnings
                 [],
             ]
             txtfilters = []
             txtpats = [
               [
                 ('\s$', 'trailing whitespace'),
                 ('.. note::[ \n][^\n]', 'add two newlines after note::')
               ],
               []
             ]
             cpats = [
               [
                 (r'//', "don't use //-style comments"),
                 (r'\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)$', r'^#!.*python', pyfilters, pypats),
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', [], pynfpats),
                 ('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())