upstream/mercurial-mirror Commit - r32599:071423d0

1

#!/usr/bin/env python

1

#!/usr/bin/env python

2

#

2

#

3

# check-code - a style and portability checker for Mercurial

3

# check-code - a style and portability checker for Mercurial

4

#

4

#

5

6

#

6

#

7

# This software may be used and distributed according to the terms of the

7

# This software may be used and distributed according to the terms of the

8

# GNU General Public License version 2 or any later version.

8

# GNU General Public License version 2 or any later version.

9

10

"""style and portability checker for Mercurial

10

"""style and portability checker for Mercurial

11

12

when a rule triggers wrong, do one of the following (prefer one from top):

12

when a rule triggers wrong, do one of the following (prefer one from top):

13

* do the work-around the rule suggests

13

* do the work-around the rule suggests

14

* doublecheck that it is a false match

14

* doublecheck that it is a false match

15

* improve the rule pattern

15

* improve the rule pattern

16

* add an ignore pattern to the rule (3rd arg) which matches your good line

16

* add an ignore pattern to the rule (3rd arg) which matches your good line

17

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

17

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

18

* change the pattern to a warning and list the exception in test-check-code-hg

18

* change the pattern to a warning and list the exception in test-check-code-hg

19

* ONLY use no--check-code for skipping entire files from external sources

19

* ONLY use no--check-code for skipping entire files from external sources

20

"""

20

"""

21

22

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

def opentext(f):

32

def opentext(f):

33

return open(f, encoding='ascii')

33

return open(f, encoding='ascii')

34

try:

34

try:

35

xrange

35

xrange

36

except NameError:

36

except NameError:

37

xrange = range

37

xrange = range

38

try:

38

try:

39

import re2

39

import re2

40

except ImportError:

40

except ImportError:

41

re2 = None

41

re2 = None

42

43

def compilere(pat, multiline=False):

43

def compilere(pat, multiline=False):

44

if multiline:

44

if multiline:

45

pat = '(?m)' + pat

45

pat = '(?m)' + pat

46

if re2:

46

if re2:

47

try:

47

try:

48

return re2.compile(pat)

48

return re2.compile(pat)

49

except re2.error:

49

except re2.error:

50

pass

50

pass

51

return re.compile(pat)

51

return re.compile(pat)

52

53

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

53

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

54

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

54

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

55

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

55

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

56

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

56

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

57

def _repquoteencodechr(i):

57

def _repquoteencodechr(i):

58

if i > 255:

58

if i > 255:

59

return 'u'

59

return 'u'

60

c = chr(i)

60

c = chr(i)

61

if c in _repquotefixedmap:

61

if c in _repquotefixedmap:

62

return _repquotefixedmap[c]

62

return _repquotefixedmap[c]

63

if c.isalpha():

63

if c.isalpha():

64

return 'x'

64

return 'x'

65

if c.isdigit():

65

if c.isdigit():

66

return 'n'

66

return 'n'

67

return 'o'

67

return 'o'

68

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

68

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

69

70

def repquote(m):

70

def repquote(m):

71

t = m.group('text')

71

t = m.group('text')

72

t = t.translate(_repquotett)

72

t = t.translate(_repquotett)

73

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

73

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

74

75

def reppython(m):

75

def reppython(m):

76

comment = m.group('comment')

76

comment = m.group('comment')

77

if comment:

77

if comment:

78

l = len(comment.rstrip())

78

l = len(comment.rstrip())

79

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

79

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

80

return repquote(m)

80

return repquote(m)

81

82

def repcomment(m):

82

def repcomment(m):

83

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

83

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

84

85

def repccomment(m):

85

def repccomment(m):

86

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

86

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

87

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

87

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

88

89

def repcallspaces(m):

89

def repcallspaces(m):

90

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

90

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

91

return m.group(1) + t

91

return m.group(1) + t

92

93

def repinclude(m):

93

def repinclude(m):

94

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

94

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

95

96

def rephere(m):

96

def rephere(m):

97

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

97

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

98

return m.group(1) + t

98

return m.group(1) + t

99

100

101

testpats = [

101

testpats = [

102

[

102

[

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

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

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

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

120

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

121

"use egrep for extended grep syntax"),

121

"use egrep for extended grep syntax"),

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

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

146

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

147

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

147

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

148

],

148

],

149

# warnings

149

# warnings

150

[

150

[

151

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

151

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

152

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

152

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

153

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

153

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

154

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

154

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

155

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

155

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

156

]

156

]

157

]

157

]

158

159

testfilters = [

159

testfilters = [

160

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

160

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

161

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

161

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

162

]

162

]

163

164

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

164

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

165

uprefix = r"^ \$ "

165

uprefix = r"^ \$ "

166

utestpats = [

166

utestpats = [

167

[

167

[

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

"explicit exit code checks unnecessary"),

174

"explicit exit code checks unnecessary"),

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

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

181

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

182

winglobmsg),

182

winglobmsg),

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

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

207

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

208

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

208

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

209

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

209

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

210

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

210

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

211

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

211

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

212

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

212

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

213

],

213

],

214

# warnings

214

# warnings

215

[

215

[

216

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

216

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

217

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

217

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

218

]

218

]

219

]

219

]

220

221

for i in [0, 1]:

221

for i in [0, 1]:

222

for tp in testpats[i]:

222

for tp in testpats[i]:

223

p = tp[0]

223

p = tp[0]

224

m = tp[1]

224

m = tp[1]

225

if p.startswith(r'^'):

225

if p.startswith(r'^'):

226

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

226

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

227

else:

227

else:

228

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

228

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

229

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

229

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

230

231

utestfilters = [

231

utestfilters = [

232

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

232

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

233

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

233

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

234

]

234

]

235

236

pypats = [

236

pypats = [

237

[

237

[

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

'dict-from-generator'),

245

'dict-from-generator'),

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

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

256

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

257

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

257

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

258

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

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

"don't use camelcase in identifiers"),

262

"don't use camelcase in identifiers"),

263

263

264

"linebreak after :"),

264

"linebreak after :"),

265

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

265

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

266

r'#.*old-style'),

266

r'#.*old-style'),

267

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

267

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

268

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

268

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

269

r'#.*old-style'),

269

r'#.*old-style'),

270

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

270

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

271

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

271

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

272

"Python keyword is not a function"),

272

"Python keyword is not a function"),

273

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

273

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

274

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

274

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

275

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

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

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

280

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

281

"gratuitous whitespace after Python keyword"),

281

"gratuitous whitespace after Python keyword"),

282

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

282

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

283

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

283

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

284

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

284

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

285

"missing whitespace around operator"),

285

"missing whitespace around operator"),

286

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

286

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

287

"missing whitespace around operator"),

287

"missing whitespace around operator"),

288

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

288

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

289

"missing whitespace around operator"),

289

"missing whitespace around operator"),

290

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

290

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

291

"wrong whitespace around ="),

291

"wrong whitespace around ="),

292

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

292

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

293

"no whitespace around = for named parameters"),

293

"no whitespace around = for named parameters"),

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

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

306

"use opener.read() instead"),

306

"use opener.read() instead"),

307

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

307

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

308

"use opener.write() instead"),

308

"use opener.write() instead"),

309

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

309

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

310

"use util.readfile() instead"),

310

"use util.readfile() instead"),

311

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

311

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

312

"use util.writefile() instead"),

312

"use util.writefile() instead"),

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

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

337

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

337

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

338

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

338

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

339

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

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

344

"use mercurial.policy.importmod instead"),

343

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

345

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

344

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

346

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

345

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

347

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

346

348

347

# rules depending on implementation of repquote()

349

# rules depending on implementation of repquote()

348

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

350

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

349

'string join across lines with no space'),

351

'string join across lines with no space'),

350

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

352

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

351

[ \t\n#]*

353

[ \t\n#]*

352

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

354

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

353

# contains translatable message)

355

# contains translatable message)

354

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

356

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

355

(?# sequence consisting of below might precede translatable message

357

(?# sequence consisting of below might precede translatable message

356

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

358

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

357

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

359

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

358

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

360

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

359

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

361

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

360

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

362

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

361

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

363

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

362

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

364

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

363

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

365

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

364

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

366

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

365

],

367

],

366

# warnings

368

# warnings

367

[

369

[

368

# rules depending on implementation of repquote()

370

# rules depending on implementation of repquote()

369

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

371

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

370

]

372

]

371

]

373

]

372

374

373

pyfilters = [

375

pyfilters = [

374

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

376

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

375

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

377

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

376

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

378

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

377

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

379

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

378

]

380

]

379

381

380

# extension non-filter patterns

382

# extension non-filter patterns

381

pyextnfpats = [

383

pyextnfpats = [

382

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

384

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

383

# warnings

385

# warnings

384

[],

386

[],

385

]

387

]

386

388

387

txtfilters = []

389

txtfilters = []

388

390

389

txtpats = [

391

txtpats = [

390

[

392

[

391

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

393

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

392

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

394

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

393

],

395

],

394

[]

396

[]

395

]

397

]

396

398

397

cpats = [

399

cpats = [

398

[

400

[

399

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

401

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

400

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

402

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

401

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

403

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

402

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

404

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

403

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

405

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

404

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

406

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

405

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

407

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

406

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

408

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

407

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

409

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

408

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

410

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

409

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

411

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

410

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

412

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

411

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

413

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

412

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

414

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

413

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

415

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

414

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

416

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

415

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

417

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

416

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

418

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

417

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

419

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

418

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

420

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

419

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

421

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

420

422

421

# rules depending on implementation of repquote()

423

# rules depending on implementation of repquote()

422

],

424

],

423

# warnings

425

# warnings

424

[

426

[

425

# rules depending on implementation of repquote()

427

# rules depending on implementation of repquote()

426

]

428

]

427

]

429

]

428

430

429

cfilters = [

431

cfilters = [

430

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

432

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

431

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

433

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

432

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

434

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

433

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

435

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

434

]

436

]

435

437

436

inutilpats = [

438

inutilpats = [

437

[

439

[

438

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

440

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

439

],

441

],

440

# warnings

442

# warnings

441

[]

443

[]

442

]

444

]

443

445

444

inrevlogpats = [

446

inrevlogpats = [

445

[

447

[

446

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

448

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

447

],

449

],

448

# warnings

450

# warnings

449

[]

451

[]

450

]

452

]

451

453

452

webtemplatefilters = []

454

webtemplatefilters = []

453

455

454

webtemplatepats = [

456

webtemplatepats = [

455

[],

457

[],

456

[

458

[

457

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

459

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

458

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

460

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

459

]

461

]

460

]

462

]

461

463

462

allfilesfilters = []

464

allfilesfilters = []

463

465

464

allfilespats = [

466

allfilespats = [

465

[

467

[

466

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

468

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

467

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

469

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

468

(r'mercurial@selenic\.com',

470

(r'mercurial@selenic\.com',

469

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

471

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

470

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

472

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

471

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

473

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

472

],

474

],

473

# warnings

475

# warnings

474

[],

476

[],

475

]

477

]

476

478

477

py3pats = [

479

py3pats = [

478

[

480

[

479

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

481

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

480

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

482

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

481

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

483

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

482

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

484

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

483

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

485

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

484

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

486

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

485

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

487

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

486

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

488

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

487

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

489

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

488

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

490

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

489

],

491

],

490

# warnings

492

# warnings

491

[],

493

[],

492

]

494

]

493

495

494

checks = [

496

checks = [

495

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

497

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

496

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

498

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

497

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

499

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

498

'', pyfilters, py3pats),

500

'', pyfilters, py3pats),

499

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

501

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

500

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

502

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

501

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

503

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

502

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

504

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

503

pyfilters, inrevlogpats),

505

pyfilters, inrevlogpats),

504

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

506

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

505

inutilpats),

507

inutilpats),

506

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

508

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

507

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

509

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

508

webtemplatefilters, webtemplatepats),

510

webtemplatefilters, webtemplatepats),

509

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

511

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

510

allfilesfilters, allfilespats),

512

allfilesfilters, allfilespats),

511

]

513

]

512

514

513

def _preparepats():

515

def _preparepats():

514

for c in checks:

516

for c in checks:

515

failandwarn = c[-1]

517

failandwarn = c[-1]

516

for pats in failandwarn:

518

for pats in failandwarn:

517

for i, pseq in enumerate(pats):

519

for i, pseq in enumerate(pats):

518

# fix-up regexes for multi-line searches

520

# fix-up regexes for multi-line searches

519

p = pseq[0]

521

p = pseq[0]

520

# \s doesn't match \n

522

# \s doesn't match \n

521

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

523

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

522

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

524

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

523

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

525

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

524

526

525

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

527

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

526

filters = c[3]

528

filters = c[3]

527

for i, flt in enumerate(filters):

529

for i, flt in enumerate(filters):

528

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

530

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

529

531

530

class norepeatlogger(object):

532

class norepeatlogger(object):

531

def __init__(self):

533

def __init__(self):

532

self._lastseen = None

534

self._lastseen = None

533

535

534

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

536

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

535

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

537

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

536

538

537

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

539

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

538

of multiple errors.

540

of multiple errors.

539

541

540

:fname: filename

542

:fname: filename

541

:lineno: line number

543

:lineno: line number

542

:line: actual content of the line

544

:line: actual content of the line

543

:msg: error message

545

:msg: error message

544

"""

546

"""

545

msgid = fname, lineno, line

547

msgid = fname, lineno, line

546

if msgid != self._lastseen:

548

if msgid != self._lastseen:

547

if blame:

549

if blame:

548

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

550

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

549

else:

551

else:

550

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

552

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

551

print(" > %s" % line)

553

print(" > %s" % line)

552

self._lastseen = msgid

554

self._lastseen = msgid

553

print(" " + msg)

555

print(" " + msg)

554

556

555

_defaultlogger = norepeatlogger()

557

_defaultlogger = norepeatlogger()

556

558

557

def getblame(f):

559

def getblame(f):

558

lines = []

560

lines = []

559

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

561

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

560

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

562

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

561

user, rev = start.split()

563

user, rev = start.split()

562

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

564

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

563

return lines

565

return lines

564

566

565

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

567

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

566

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

568

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

567

"""checks style and portability of a given file

569

"""checks style and portability of a given file

568

570

569

:f: filepath

571

:f: filepath

570

:logfunc: function used to report error

572

:logfunc: function used to report error

571

logfunc(filename, linenumber, linecontent, errormessage)

573

logfunc(filename, linenumber, linecontent, errormessage)

572

:maxerr: number of error to display before aborting.

574

:maxerr: number of error to display before aborting.

573

Set to false (default) to report all errors

575

Set to false (default) to report all errors

574

576

575

return True if no error is found, False otherwise.

577

return True if no error is found, False otherwise.

576

"""

578

"""

577

blamecache = None

579

blamecache = None

578

result = True

580

result = True

579

581

580

try:

582

try:

581

with opentext(f) as fp:

583

with opentext(f) as fp:

582

try:

584

try:

583

pre = post = fp.read()

585

pre = post = fp.read()

584

except UnicodeDecodeError as e:

586

except UnicodeDecodeError as e:

585

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

587

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

586

return result

588

return result

587

except IOError as e:

589

except IOError as e:

588

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

590

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

589

return result

591

return result

590

592

591

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

593

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

592

post = pre # discard filtering result of previous check

594

post = pre # discard filtering result of previous check

593

if debug:

595

if debug:

594

print(name, f)

596

print(name, f)

595

fc = 0

597

fc = 0

596

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

598

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

597

if debug:

599

if debug:

598

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

600

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

599

name, match, f))

601

name, match, f))

600

continue

602

continue

601

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

603

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

602

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

604

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

603

# no- check- code

605

# no- check- code

604

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

606

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

605

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

607

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

606

# spelling, we write it with the expected spelling from

608

# spelling, we write it with the expected spelling from

607

# tests/test-check-code.t

609

# tests/test-check-code.t

608

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

610

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

609

return "Skip" # skip checking this file

611

return "Skip" # skip checking this file

610

for p, r in filters:

612

for p, r in filters:

611

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

613

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

612

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

614

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

613

if warnings:

615

if warnings:

614

pats = pats[0] + pats[1]

616

pats = pats[0] + pats[1]

615

else:

617

else:

616

pats = pats[0]

618

pats = pats[0]

617

# print post # uncomment to show filtered version

619

# print post # uncomment to show filtered version

618

620

619

if debug:

621

if debug:

620

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

622

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

621

623

622

prelines = None

624

prelines = None

623

errors = []

625

errors = []

624

for i, pat in enumerate(pats):

626

for i, pat in enumerate(pats):

625

if len(pat) == 3:

627

if len(pat) == 3:

626

p, msg, ignore = pat

628

p, msg, ignore = pat

627

else:

629

else:

628

p, msg = pat

630

p, msg = pat

629

ignore = None

631

ignore = None

630

if i >= nerrs:

632

if i >= nerrs:

631

msg = "warning: " + msg

633

msg = "warning: " + msg

632

634

633

pos = 0

635

pos = 0

634

n = 0

636

n = 0

635

for m in p.finditer(post):

637

for m in p.finditer(post):

636

if prelines is None:

638

if prelines is None:

637

prelines = pre.splitlines()

639

prelines = pre.splitlines()

638

postlines = post.splitlines(True)

640

postlines = post.splitlines(True)

639

641

640

start = m.start()

642

start = m.start()

641

while n < len(postlines):

643

while n < len(postlines):

642

step = len(postlines[n])

644

step = len(postlines[n])

643

if pos + step > start:

645

if pos + step > start:

644

break

646

break

645

pos += step

647

pos += step

646

n += 1

648

n += 1

647

l = prelines[n]

649

l = prelines[n]

648

650

649

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

651

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

650

if debug:

652

if debug:

651

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

653

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

652

name, f, n))

654

name, f, n))

653

continue

655

continue

654

bd = ""

656

bd = ""

655

if blame:

657

if blame:

656

bd = 'working directory'

658

bd = 'working directory'

657

if not blamecache:

659

if not blamecache:

658

blamecache = getblame(f)

660

blamecache = getblame(f)

659

if n < len(blamecache):

661

if n < len(blamecache):

660

bl, bu, br = blamecache[n]

662

bl, bu, br = blamecache[n]

661

if bl == l:

663

if bl == l:

662

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

664

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

663

665

664

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

666

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

665

result = False

667

result = False

666

668

667

errors.sort()

669

errors.sort()

668

for e in errors:

670

for e in errors:

669

logfunc(*e)

671

logfunc(*e)

670

fc += 1

672

fc += 1

671

if maxerr and fc >= maxerr:

673

if maxerr and fc >= maxerr:

672

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

674

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

673

break

675

break

674

676

675

return result

677

return result

676

678

677

def main():

679

def main():

678

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

680

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

679

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

681

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

680

help="include warning-level checks")

682

help="include warning-level checks")

681

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

683

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

682

help="max warnings per file")

684

help="max warnings per file")

683

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

685

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

684

help="use annotate to generate blame info")

686

help="use annotate to generate blame info")

685

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

687

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

686

help="show debug information")

688

help="show debug information")

687

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

689

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

688

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

690

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

689

691

690

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

692

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

691

lineno=True)

693

lineno=True)

692

(options, args) = parser.parse_args()

694

(options, args) = parser.parse_args()

693

695

694

if len(args) == 0:

696

if len(args) == 0:

695

check = glob.glob("*")

697

check = glob.glob("*")

696

elif args == ['-']:

698

elif args == ['-']:

697

# read file list from stdin

699

# read file list from stdin

698

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

700

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

699

else:

701

else:

700

check = args

702

check = args

701

703

702

_preparepats()

704

_preparepats()

703

705

704

ret = 0

706

ret = 0

705

for f in check:

707

for f in check:

706

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

708

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

707

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

709

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

708

lineno=options.lineno):

710

lineno=options.lineno):

709

ret = 1

711

ret = 1

710

return ret

712

return ret

711

713

712

if __name__ == "__main__":

714

if __name__ == "__main__":

713

sys.exit(main())

715

sys.exit(main())

	Site-wide shortcuts
/	Use quick search box
g h	Goto home page
g g	Goto my private gists page
g G	Goto my public gists page
g 0-9	Goto bookmarked items from 0-9
n r	New repository page
n g	New gist page

	Repositories
g s	Goto summary page
g c	Goto changelog page
g f	Goto files page
g F	Goto files page with file search activated
g p	Goto pull requests page
g o	Goto repository settings
g O	Goto repository access permissions settings
t s	Toggle sidebar on some pages

             #!/usr/bin/env python
             #
             # check-code - a style and portability checker for Mercurial
             #
             # Copyright 2010 Matt Mackall <mpm@selenic.com>
             #
             # This software may be used and distributed according to the terms of the
             # GNU General Public License version 2 or any later version.
             """style and portability checker for Mercurial
             when a rule triggers wrong, do one of the following (prefer one from top):
              * do the work-around the rule suggests
              * doublecheck that it is a false match
              * improve the rule pattern
              * add an ignore pattern to the rule (3rd arg) which matches your good line
                (you can append a short comment and match this, like: #re-raises)
              * change the pattern to a warning and list the exception in test-check-code-hg
              * ONLY use no--check-code for skipping entire files from external sources
             """
             from __future__ import absolute_import, print_function
             import glob
             import keyword
             import optparse
             import os
             import re
             import sys
             if sys.version_info[0] < 3:
                 opentext = open
             else:
                 def opentext(f):
                     return open(f, encoding='ascii')
             try:
                 xrange
             except NameError:
                 xrange = range
             try:
                 import re2
             except ImportError:
                 re2 = None
             def compilere(pat, multiline=False):
                 if multiline:
                     pat = '(?m)' + pat
                 if re2:
                     try:
                         return re2.compile(pat)
                     except re2.error:
                         pass
                 return re.compile(pat)
             # check "rules depending on implementation of repquote()" in each
             # patterns (especially pypats), before changing around repquote()
             _repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
                                  '%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}
             def _repquoteencodechr(i):
                 if i > 255:
                     return 'u'
                 c = chr(i)
                 if c in _repquotefixedmap:
                     return _repquotefixedmap[c]
                 if c.isalpha():
                     return 'x'
                 if c.isdigit():
                     return 'n'
                 return 'o'
             _repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))
             def repquote(m):
                 t = m.group('text')
                 t = t.translate(_repquotett)
                 return m.group('quote') + t + m.group('quote')
             def reppython(m):
                 comment = m.group('comment')
                 if comment:
                     l = len(comment.rstrip())
                     return "#" * l + comment[l:]
                 return repquote(m)
             def repcomment(m):
                 return m.group(1) + "#" * len(m.group(2))
             def repccomment(m):
                 t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
                 return m.group(1) + t + "*/"
             def repcallspaces(m):
                 t = re.sub(r"\n\s+", "\n", m.group(2))
                 return m.group(1) + t
             def repinclude(m):
                 return m.group(1) + "<foo>"
             def rephere(m):
                 t = re.sub(r"\S", "x", m.group(2))
                 return m.group(1) + t
             testpats = [
               [
                 (r'\b(push|pop)d\b', "don't use 'pushd' or 'popd', use 'cd'"),
                 (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
                 (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
                 (r'(?<!hg )grep.* -a', "don't use 'grep -a', use in-line python"),
                 (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
                 (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
                 (r'echo -n', "don't use 'echo -n', use printf"),
                 (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
                 (r'head -c', "don't use 'head -c', use 'dd'"),
                 (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
                 (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
                 (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
                 (r'printf.*[^\\]\\([1-9]|0\d)', r"don't use 'printf \NNN', use Python"),
                 (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
                 (r'\$\(.*\)', "don't use $(expr), use `expr`"),
                 (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
                 (r'\[[^\]]+==', '[ foo == bar ] is a bashism, use [ foo = bar ] instead'),
                 (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                  "use egrep for extended grep syntax"),
                 (r'/bin/', "don't use explicit paths for tools"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'export .*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                 (r'\bls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
                 (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
                 (r'^stop\(\)', "don't use 'stop' as a shell function name"),
                 (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
                 (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
                 (r'^alias\b.*=', "don't use alias, use a function"),
                 (r'if\s*!', "don't use '!' to negate exit status"),
                 (r'/dev/u?random', "don't use entropy, use /dev/zero"),
                 (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
                 (r'^( *)\t', "don't use tabs to indent"),
                 (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
                  "put a backslash-escaped newline after sed 'i' command"),
                 (r'^diff *-\w*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
                 (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'\|&', "don't use |&, use 2>&1"),
                 (r'\w =  +\w', "only one space after = allowed"),
                 (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
                 (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),
                 (r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),
               ],
               # warnings
               [
                 (r'^function', "don't use 'function', use old style"),
                 (r'^diff.*-\w*N', "don't use 'diff -N'"),
                 (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
                 (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
                 (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
               ]
             ]
             testfilters = [
                 (r"( *)(#([^\n]*\S)?)", repcomment),
                 (r"<<(\S+)((.|\n)*?\n\1)", rephere),
             ]
             winglobmsg = "use (glob) to match Windows paths too"
             uprefix = r"^  \$ "
             utestpats = [
               [
                 (r'^(\S.*||  [$>] \S.*)[ \t]\n', "trailing whitespace on non-output"),
                 (uprefix + r'.*\|\s*sed[^|>\n]*\n',
                  "use regex test output patterns instead of sed"),
                 (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
                 (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
                 (uprefix + r'.*\|\| echo.*(fail|error)',
                  "explicit exit code checks unnecessary"),
                 (uprefix + r'set -e', "don't use set -e"),
                 (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
                 (uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "
                  "as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx
                  '# no-msys'), # in test-pull.t which is skipped on windows
                 (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
                 (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
                  winglobmsg),
                 (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
                  '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
                 (r'^  reverting (?!subrepo ).*/.*[^)]$', winglobmsg),
                 (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
                 (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
                 (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
                 (r'^  moving \S+/.*[^)]$', winglobmsg),
                 (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
                 (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
                 (r'^  .*file://\$TESTTMP',
                  'write "file:/*/$TESTTMP" + (glob) to match on windows too'),
                 (r'^  [^$>].*27\.0\.0\.1',
                  'use $LOCALIP not an explicit loopback address'),
                 (r'^  [^$>].*\$LOCALIP.*[^)]$',
                  'mark $LOCALIP output lines with (glob) to help tests in BSD jails'),
                 (r'^  (cat|find): .*: No such file or directory',
                  'use test -f to test for file existence'),
                 (r'^  diff -[^ -]*p',
                  "don't use (external) diff with -p for portability"),
                 (r'^  [-+][-+][-+] .* [-+]0000 \(glob\)',
                  "glob timezone field in diff output for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',
                  "use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N* +N* @@ (glob)' style chunk header for portability"),
                 (uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'
                  r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',
                  "use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),
               ],
               # warnings
               [
                 (r'^  (?!.*\$LOCALIP)[^*?/\n]* \(glob\)$',
                  "glob match with no glob string (?, *, /, and $LOCALIP)"),
               ]
             ]
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%s)" % p[1:]
                     else:
                         p = r"^  [$>] .*(%s)" % p
                     utestpats[i].append((p, m) + tp[2:])
             utestfilters = [
                 (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
                 (r"( +)(#([^\n]*\S)?)", repcomment),
             ]
             pypats = [
               [
                 (r'^\s*def\s*\w+\s*\(.*,\s*\(',
                  "tuple parameter unpacking not available in Python 3+"),
                 (r'lambda\s*\(.*,.*\)',
                  "tuple parameter unpacking not available in Python 3+"),
                 (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
                 (r'(?<!\.)\breduce\s*\(.*', "reduce is not available in Python 3+"),
                 (r'\bdict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
                  'dict-from-generator'),
                 (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
                 (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
                 (r'^\s*\t', "don't use tabs"),
                 (r'\S;\s*\n', "semicolon"),
                 (r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
                 (r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
                 (r'(\w|\)),\w', "missing whitespace after ,"),
                 (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
                 (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
                 (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'.{81}', "line too long"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
             #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
             #     "don't use underbars in identifiers"),
                 (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
                  "don't use camelcase in identifiers"),
                 (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                  "linebreak after :"),
                 (r'class\s[^( \n]+:', "old-style class, use class foo(object)",
                  r'#.*old-style'),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)",
                  r'#.*old-style'),
                 (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                                         if k not in ('print', 'exec')),
                  "Python keyword is not a function"),
                 (r',]', "unneeded trailing ',' in list"),
             #    (r'class\s[A-Z][^\(]*\((?!Exception)',
             #     "don't capitalize non-exception classes"),
             #    (r'in range\(', "use xrange"),
             #    (r'^\s*print\s+', "avoid using print in core and extensions"),
                 (r'[\x80-\xff]', "non-ASCII character literal"),
                 (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
                 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
                  "gratuitous whitespace after Python keyword"),
                 (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
             #    (r'\s\s=', "gratuitous whitespace before ="),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
                  "missing whitespace around operator"),
                 (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
                  "wrong whitespace around ="),
                 (r'\([^()]*( =[^=]|[^<>!=]= )',
                  "no whitespace around = for named parameters"),
                 (r'raise Exception', "don't raise generic exceptions"),
                 (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                  "don't use old-style two-argument raise, use Exception(message)"),
                 (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                 (r' [=!]=\s+(True|False|None)',
                  "comparison with singleton, use 'is' or 'is not' instead"),
                 (r'^\s*(while|if) [01]:',
                  "use True/False for constant Boolean expression"),
                 (r'(?:(?<!def)\s+|\()hasattr\(',
                  'hasattr(foo, bar) is broken on py2, use util.safehasattr(foo, bar) '
                  'instead', r'#.*hasattr-py3-only'),
                 (r'opener\([^)]*\).read\(',
                  "use opener.read() instead"),
                 (r'opener\([^)]*\).write\(',
                  "use opener.write() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.read\(',
                  "use util.readfile() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.write\(',
                  "use util.writefile() instead"),
                 (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'[\s\(](open|file)\([^)]*\)\.',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
                 (r'\.debug\(\_', "don't mark debug messages for translation"),
                 (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
                 (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
                 (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
                  'legacy exception syntax; use "as" instead of ","'),
                 (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                 (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
                 (r'\bdef\s+__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
                 (r'os\.path\.join\(.*, *(""|\'\')\)',
                  "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
                 (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
                 # XXX only catch mutable arguments on the first line of the definition
                 (r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'^@(\w*\.)?cachefunc', "module-level @cachefunc is risky, please avoid"),
                 (r'^import Queue', "don't use Queue, use util.queue + util.empty"),
                 (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),
                 (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
                 (r'^import SocketServer', "don't use SockerServer, use util.socketserver"),
                 (r'^import urlparse', "don't use urlparse, use util.urlreq"),
                 (r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),
                 (r'^import cPickle', "don't use cPickle, use util.pickle"),
                 (r'^import pickle', "don't use pickle, use util.pickle"),
                 (r'^import httplib', "don't use httplib, use util.httplib"),
                 (r'^import BaseHTTPServer', "use util.httpserver instead"),
+                (r'^(from|import) mercurial\.(cext|pure|cffi)',
+                 "use mercurial.policy.importmod instead"),
                 (r'\.next\(\)', "don't use .next(), use next(...)"),
                 (r'([a-z]*).revision\(\1\.node\(',
                  "don't convert rev to node before passing to revision(nodeorrev)"),
                 # rules depending on implementation of repquote()
                 (r' x+[xpqo%APM][\'"]\n\s+[\'"]x',
                  'string join across lines with no space'),
                 (r'''(?x)ui\.(status|progress|write|note|warn)\(
                      [ \t\n#]*
                      (?# any strings/comments might precede a string, which
                        # contains translatable message)
                      ((['"]|\'\'\'|""")[ \npq%bAPMxno]*(['"]|\'\'\'|""")[ \t\n#]+)*
                      (?# sequence consisting of below might precede translatable message
                        # - formatting string: "% 10s", "%05d", "% -3.2f", "%*s", "%%" ...
                        # - escaped character: "\\", "\n", "\0" ...
                        # - character other than '%', 'b' as '\', and 'x' as alphabet)
                      (['"]|\'\'\'|""")
                      ((%([ n]?[PM]?([np]+|A))?x)|%%|b[bnx]|[ \nnpqAPMo])*x
                      (?# this regexp can't use [^...] style,
                        # because _preparepats forcibly adds "\n" into [^...],
                        # even though this regexp wants match it against "\n")''',
                  "missing _() in ui message (use () to hide false-positives)"),
               ],
               # warnings
               [
                 # rules depending on implementation of repquote()
                 (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
               ]
             ]
             pyfilters = [
                 (r"""(?msx)(?P<comment>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""", reppython),
             ]
             # extension non-filter patterns
             pyextnfpats = [
                 [(r'^"""\n?[A-Z]', "don't capitalize docstring title")],
                 # warnings
                 [],
             ]
             txtfilters = []
             txtpats = [
               [
                 ('\s$', 'trailing whitespace'),
                 ('.. note::[ \n][^\n]', 'add two newlines after note::')
               ],
               []
             ]
             cpats = [
               [
                 (r'//', "don't use //-style comments"),
                 (r'^  ', "don't use spaces to indent"),
                 (r'\S\t', "don't use tabs except for indent"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
                 (r'.{81}', "line too long"),
                 (r'(while|if|do|for)\(', "use space after while/if/do/for"),
                 (r'return\(', "return is not a function"),
                 (r' ;', "no space before ;"),
                 (r'[^;] \)', "no space before )"),
                 (r'[)][{]', "space between ) and {"),
                 (r'\w+\* \w+', "use int *foo, not int* foo"),
                 (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
                 (r'\w+ (\+\+|--)', "use foo++, not foo ++"),
                 (r'\w,\w', "missing whitespace after ,"),
                 (r'^[^#]\w[+/*]\w', "missing whitespace in expression"),
                 (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'^#\s+\w', "use #foo, not # foo"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'^\s*#import\b', "use only #include in standard C code"),
                 (r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),
                 (r'strcat\(', "don't use strcat"),
                 # rules depending on implementation of repquote()
               ],
               # warnings
               [
                 # rules depending on implementation of repquote()
               ]
             ]
             cfilters = [
                 (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
                 (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
                 (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
                 (r'(\()([^)]+\))', repcallspaces),
             ]
             inutilpats = [
               [
                 (r'\bui\.', "don't use ui in util"),
               ],
               # warnings
               []
             ]
             inrevlogpats = [
               [
                 (r'\brepo\.', "don't use repo in revlog"),
               ],
               # warnings
               []
             ]
             webtemplatefilters = []
             webtemplatepats = [
               [],
               [
                 (r'{desc(\|(?!websub|firstline)[^\|]*)+}',
                  'follow desc keyword with either firstline or websub'),
               ]
             ]
             allfilesfilters = []
             allfilespats = [
               [
                 (r'(http|https)://[a-zA-Z0-9./]*selenic.com/',
                  'use mercurial-scm.org domain URL'),
                 (r'mercurial@selenic\.com',
                  'use mercurial-scm.org domain for mercurial ML address'),
                 (r'mercurial-devel@selenic\.com',
                  'use mercurial-scm.org domain for mercurial-devel ML address'),
               ],
               # warnings
               [],
             ]
             py3pats = [
               [
                 (r'os\.environ', "use encoding.environ instead (py3)", r'#.*re-exports'),
                 (r'os\.name', "use pycompat.osname instead (py3)"),
                 (r'os\.getcwd', "use pycompat.getcwd instead (py3)"),
                 (r'os\.sep', "use pycompat.ossep instead (py3)"),
                 (r'os\.pathsep', "use pycompat.ospathsep instead (py3)"),
                 (r'os\.altsep', "use pycompat.osaltsep instead (py3)"),
                 (r'sys\.platform', "use pycompat.sysplatform instead (py3)"),
                 (r'getopt\.getopt', "use pycompat.getoptb instead (py3)"),
                 (r'os\.getenv', "use encoding.environ.get instead"),
                 (r'os\.setenv', "modifying the environ dict is not preferred"),
               ],
               # warnings
               [],
             ]
             checks = [
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
                 ('python', r'.*hgext.*\.py$', '', [], pyextnfpats),
                 ('python 3', r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',
                  '', pyfilters, py3pats),
                 ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),
                 ('c', r'.*\.[ch]$', '', cfilters, cpats),
                 ('unified test', r'.*\.t$', '', utestfilters, utestpats),
                 ('layering violation repo in revlog', r'mercurial/revlog\.py', '',
                  pyfilters, inrevlogpats),
                 ('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,
                  inutilpats),
                 ('txt', r'.*\.txt$', '', txtfilters, txtpats),
                 ('web template', r'mercurial/templates/.*\.tmpl', '',
                  webtemplatefilters, webtemplatepats),
                 ('all except for .po', r'.*(?<!\.po)$', '',
                  allfilesfilters, allfilespats),
             ]
             def _preparepats():
                 for c in checks:
                     failandwarn = c[-1]
                     for pats in failandwarn:
                         for i, pseq in enumerate(pats):
                             # fix-up regexes for multi-line searches
                             p = pseq[0]
                             # \s doesn't match \n
                             p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
                             # [^...] doesn't match newline
                             p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)
                             pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]
                     filters = c[3]
                     for i, flt in enumerate(filters):
                         filters[i] = re.compile(flt[0]), flt[1]
             class norepeatlogger(object):
                 def __init__(self):
                     self._lastseen = None
                 def log(self, fname, lineno, line, msg, blame):
                     """print error related a to given line of a given file.
                     The faulty line will also be printed but only once in the case
                     of multiple errors.
                     :fname: filename
                     :lineno: line number
                     :line: actual content of the line
                     :msg: error message
                     """
                     msgid = fname, lineno, line
                     if msgid != self._lastseen:
                         if blame:
                             print("%s:%d (%s):" % (fname, lineno, blame))
                         else:
                             print("%s:%d:" % (fname, lineno))
                         print(" > %s" % line)
                         self._lastseen = msgid
                     print(" " + msg)
             _defaultlogger = norepeatlogger()
             def getblame(f):
                 lines = []
                 for l in os.popen('hg annotate -un %s' % f):
                     start, line = l.split(':', 1)
                     user, rev = start.split()
                     lines.append((line[1:-1], user, rev))
                 return lines
             def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,
                           blame=False, debug=False, lineno=True):
                 """checks style and portability of a given file
                 :f: filepath
                 :logfunc: function used to report error
                           logfunc(filename, linenumber, linecontent, errormessage)
                 :maxerr: number of error to display before aborting.
                          Set to false (default) to report all errors
                 return True if no error is found, False otherwise.
                 """
                 blamecache = None
                 result = True
                 try:
                     with opentext(f) as fp:
                         try:
                             pre = post = fp.read()
                         except UnicodeDecodeError as e:
                             print("%s while reading %s" % (e, f))
                             return result
                 except IOError as e:
                     print("Skipping %s, %s" % (f, str(e).split(':', 1)[0]))
                     return result
                 for name, match, magic, filters, pats in checks:
                     post = pre # discard filtering result of previous check
                     if debug:
                         print(name, f)
                     fc = 0
                     if not (re.match(match, f) or (magic and re.search(magic, pre))):
                         if debug:
                             print("Skipping %s for %s it doesn't match %s" % (
                                    name, match, f))
                         continue
                     if "no-" "check-code" in pre:
                         # If you're looking at this line, it's because a file has:
                         # no- check- code
                         # but the reason to output skipping is to make life for
                         # tests easier. So, instead of writing it with a normal
                         # spelling, we write it with the expected spelling from
                         # tests/test-check-code.t
                         print("Skipping %s it has no-che?k-code (glob)" % f)
                         return "Skip" # skip checking this file
                     for p, r in filters:
                         post = re.sub(p, r, post)
                     nerrs = len(pats[0]) # nerr elements are errors
                     if warnings:
                         pats = pats[0] + pats[1]
                     else:
                         pats = pats[0]
                     # print post # uncomment to show filtered version
                     if debug:
                         print("Checking %s for %s" % (name, f))
                     prelines = None
                     errors = []
                     for i, pat in enumerate(pats):
                         if len(pat) == 3:
                             p, msg, ignore = pat
                         else:
                             p, msg = pat
                             ignore = None
                         if i >= nerrs:
                             msg = "warning: " + msg
                         pos = 0
                         n = 0
                         for m in p.finditer(post):
                             if prelines is None:
                                 prelines = pre.splitlines()
                                 postlines = post.splitlines(True)
                             start = m.start()
                             while n < len(postlines):
                                 step = len(postlines[n])
                                 if pos + step > start:
                                     break
                                 pos += step
                                 n += 1
                             l = prelines[n]
                             if ignore and re.search(ignore, l, re.MULTILINE):
                                 if debug:
                                     print("Skipping %s for %s:%s (ignore pattern)" % (
                                         name, f, n))
                                 continue
                             bd = ""
                             if blame:
                                 bd = 'working directory'
                                 if not blamecache:
                                     blamecache = getblame(f)
                                 if n < len(blamecache):
                                     bl, bu, br = blamecache[n]
                                     if bl == l:
                                         bd = '%s@%s' % (bu, br)
                             errors.append((f, lineno and n + 1, l, msg, bd))
                             result = False
                     errors.sort()
                     for e in errors:
                         logfunc(*e)
                         fc += 1
                         if maxerr and fc >= maxerr:
                             print(" (too many errors, giving up)")
                             break
                 return result
             def main():
                 parser = optparse.OptionParser("%prog [options] [files | -]")
                 parser.add_option("-w", "--warnings", action="store_true",
                                   help="include warning-level checks")
                 parser.add_option("-p", "--per-file", type="int",
                                   help="max warnings per file")
                 parser.add_option("-b", "--blame", action="store_true",
                                   help="use annotate to generate blame info")
                 parser.add_option("", "--debug", action="store_true",
                                   help="show debug information")
                 parser.add_option("", "--nolineno", action="store_false",
                                   dest='lineno', help="don't show line numbers")
                 parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                                     lineno=True)
                 (options, args) = parser.parse_args()
                 if len(args) == 0:
                     check = glob.glob("*")
                 elif args == ['-']:
                     # read file list from stdin
                     check = sys.stdin.read().splitlines()
                 else:
                     check = args
                 _preparepats()
                 ret = 0
                 for f in check:
                     if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                                      blame=options.blame, debug=options.debug,
                                      lineno=options.lineno):
                         ret = 1
                 return ret
             if __name__ == "__main__":
                 sys.exit(main())