upstream/mercurial-mirror Commit - r31824:48046444

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'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),

103

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

119

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

120

"use egrep for extended grep syntax"),

120

"use egrep for extended grep syntax"),

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

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

146

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

147

],

147

],

148

# warnings

148

# warnings

149

[

149

[

150

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

150

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

151

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

151

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

152

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

152

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

153

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

153

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

154

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

154

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

155

]

155

]

156

]

156

]

157

158

testfilters = [

158

testfilters = [

159

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

159

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

160

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

160

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

161

]

161

]

162

163

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

163

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

164

uprefix = r"^ \$ "

164

uprefix = r"^ \$ "

165

utestpats = [

165

utestpats = [

166

[

166

[

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

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

173

"explicit exit code checks unnecessary"),

173

"explicit exit code checks unnecessary"),

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

winglobmsg),

181

winglobmsg),

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

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

207

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

208

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

208

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

209

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

209

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

210

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

210

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

211

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

211

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

212

],

212

],

213

# warnings

213

# warnings

214

[

214

[

215

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

215

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

216

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

216

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

217

]

217

]

218

]

218

]

219

220

for i in [0, 1]:

220

for i in [0, 1]:

221

for tp in testpats[i]:

221

for tp in testpats[i]:

222

p = tp[0]

222

p = tp[0]

223

m = tp[1]

223

m = tp[1]

224

if p.startswith(r'^'):

224

if p.startswith(r'^'):

225

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

225

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

226

else:

226

else:

227

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

227

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

228

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

228

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

229

230

utestfilters = [

230

utestfilters = [

231

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

231

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

232

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

232

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

233

]

233

]

234

235

pypats = [

235

pypats = [

236

[

236

[

237

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

237

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

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

'dict-from-generator'),

244

'dict-from-generator'),

245

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

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

256

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

257

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

257

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

258

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

258

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

259

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

259

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

260

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

260

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

261

"don't use camelcase in identifiers"),

261

"don't use camelcase in identifiers"),

262

262

263

"linebreak after :"),

263

"linebreak after :"),

264

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

264

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

265

r'#.*old-style'),

265

r'#.*old-style'),

266

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

266

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

267

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

267

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

268

r'#.*old-style'),

268

r'#.*old-style'),

269

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

269

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

270

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

270

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

271

"Python keyword is not a function"),

271

"Python keyword is not a function"),

272

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

272

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

273

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

273

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

274

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

274

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

275

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

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

"gratuitous whitespace after Python keyword"),

280

"gratuitous whitespace after Python keyword"),

281

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

281

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

282

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

282

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

283

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

283

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

284

"missing whitespace around operator"),

284

"missing whitespace around operator"),

285

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

285

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

286

"missing whitespace around operator"),

286

"missing whitespace around operator"),

287

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

287

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

288

"missing whitespace around operator"),

288

"missing whitespace around operator"),

289

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

289

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

290

"wrong whitespace around ="),

290

"wrong whitespace around ="),

291

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

291

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

292

"no whitespace around = for named parameters"),

292

"no whitespace around = for named parameters"),

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

"use opener.read() instead"),

304

"use opener.read() instead"),

305

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

305

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

306

"use opener.write() instead"),

306

"use opener.write() instead"),

307

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

307

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

308

"use util.readfile() instead"),

308

"use util.readfile() instead"),

309

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

309

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

310

"use util.writefile() instead"),

310

"use util.writefile() instead"),

311

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

311

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

312

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

312

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

313

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

313

(r'[\s$](open|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'(?i)descend[e]nt', "the proper spelling is descendAnt"),

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

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

337

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

337

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

338

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

338

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

339

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

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

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

344

345

# rules depending on implementation of repquote()

345

# rules depending on implementation of repquote()

346

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

346

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

347

'string join across lines with no space'),

347

'string join across lines with no space'),

348

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

348

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

349

[ \t\n#]*

349

[ \t\n#]*

350

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

350

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

351

# contains translatable message)

351

# contains translatable message)

352

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

352

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

353

(?# sequence consisting of below might precede translatable message

353

(?# sequence consisting of below might precede translatable message

354

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

354

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

355

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

355

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

356

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

356

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

357

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

357

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

358

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

358

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

359

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

359

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

360

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

360

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

361

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

361

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

362

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

362

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

363

],

363

],

364

# warnings

364

# warnings

365

[

365

[

366

# rules depending on implementation of repquote()

366

# rules depending on implementation of repquote()

367

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

367

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

368

]

368

]

369

]

369

]

370

371

pyfilters = [

371

pyfilters = [

372

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

372

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

373

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

373

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

374

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

374

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

375

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

375

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

376

]

376

]

377

378

# extension non-filter patterns

378

# extension non-filter patterns

379

pyextnfpats = [

379

pyextnfpats = [

380

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

380

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

381

# warnings

381

# warnings

382

[],

382

[],

383

]

383

]

384

385

txtfilters = []

385

txtfilters = []

386

387

txtpats = [

387

txtpats = [

388

[

388

[

389

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

389

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

390

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

390

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

391

],

391

],

392

[]

392

[]

393

]

393

]

394

395

cpats = [

395

cpats = [

396

[

396

[

397

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

397

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

398

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

398

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

399

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

399

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

400

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

400

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

401

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

401

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

402

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

402

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

403

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

403

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

404

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

404

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

405

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

405

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

406

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

406

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

407

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

407

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

408

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

408

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

409

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

409

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

410

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

410

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

411

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

411

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

412

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

412

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

413

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

413

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

414

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

414

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

415

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

415

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

416

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

416

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

417

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

417

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

418

419

# rules depending on implementation of repquote()

419

# rules depending on implementation of repquote()

420

],

420

],

421

# warnings

421

# warnings

422

[

422

[

423

# rules depending on implementation of repquote()

423

# rules depending on implementation of repquote()

424

]

424

]

425

]

425

]

426

427

cfilters = [

427

cfilters = [

428

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

428

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

429

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

429

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

430

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

430

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

431

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

431

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

432

]

432

]

433

434

inutilpats = [

434

inutilpats = [

435

[

435

[

436

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

436

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

437

],

437

],

438

# warnings

438

# warnings

439

[]

439

[]

440

]

440

]

441

442

inrevlogpats = [

442

inrevlogpats = [

443

[

443

[

444

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

444

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

445

],

445

],

446

# warnings

446

# warnings

447

[]

447

[]

448

]

448

]

449

450

webtemplatefilters = []

450

webtemplatefilters = []

451

452

webtemplatepats = [

452

webtemplatepats = [

453

[],

453

[],

454

[

454

[

455

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

455

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

456

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

456

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

457

]

457

]

458

]

458

]

459

460

allfilesfilters = []

460

allfilesfilters = []

461

462

allfilespats = [

462

allfilespats = [

463

[

463

[

464

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

464

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

465

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

465

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

466

(r'mercurial@selenic\.com',

466

(r'mercurial@selenic\.com',

467

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

467

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

468

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

468

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

469

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

469

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

470

],

470

],

471

# warnings

471

# warnings

472

[],

472

[],

473

]

473

]

474

475

py3pats = [

475

py3pats = [

476

[

476

[

477

(r'os\.environ', "use encoding.environ instead (py3)"),

477

(r'os\.environ', "use encoding.environ instead (py3)"),

478

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

478

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

479

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

479

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

480

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

480

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

481

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

481

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

482

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

482

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

483

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

483

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

484

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

484

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

485

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

485

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

486

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

486

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

487

],

487

],

488

# warnings

488

# warnings

489

[],

489

[],

490

]

490

]

491

492

checks = [

492

checks = [

493

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

493

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

494

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

494

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

495

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

495

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

496

pyfilters, py3pats),

496

pyfilters, py3pats),

497

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

497

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

498

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

498

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

499

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

499

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

500

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

500

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

501

pyfilters, inrevlogpats),

501

pyfilters, inrevlogpats),

502

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

502

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

503

inutilpats),

503

inutilpats),

504

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

504

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

505

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

505

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

506

webtemplatefilters, webtemplatepats),

506

webtemplatefilters, webtemplatepats),

507

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

507

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

508

allfilesfilters, allfilespats),

508

allfilesfilters, allfilespats),

509

]

509

]

510

511

def _preparepats():

511

def _preparepats():

512

for c in checks:

512

for c in checks:

513

failandwarn = c[-1]

513

failandwarn = c[-1]

514

for pats in failandwarn:

514

for pats in failandwarn:

515

for i, pseq in enumerate(pats):

515

for i, pseq in enumerate(pats):

516

# fix-up regexes for multi-line searches

516

# fix-up regexes for multi-line searches

517

p = pseq[0]

517

p = pseq[0]

518

# \s doesn't match \n

518

# \s doesn't match \n

519

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

519

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

520

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

520

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

521

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

521

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

522

523

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

523

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

524

filters = c[3]

524

filters = c[3]

525

for i, flt in enumerate(filters):

525

for i, flt in enumerate(filters):

526

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

526

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

527

528

class norepeatlogger(object):

528

class norepeatlogger(object):

529

def __init__(self):

529

def __init__(self):

530

self._lastseen = None

530

self._lastseen = None

531

532

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

532

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

533

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

533

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

534

535

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

535

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

536

of multiple errors.

536

of multiple errors.

537

538

:fname: filename

538

:fname: filename

539

:lineno: line number

539

:lineno: line number

540

:line: actual content of the line

540

:line: actual content of the line

541

:msg: error message

541

:msg: error message

542

"""

542

"""

543

msgid = fname, lineno, line

543

msgid = fname, lineno, line

544

if msgid != self._lastseen:

544

if msgid != self._lastseen:

545

if blame:

545

if blame:

546

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

546

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

547

else:

547

else:

548

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

548

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

549

print(" > %s" % line)

549

print(" > %s" % line)

550

self._lastseen = msgid

550

self._lastseen = msgid

551

print(" " + msg)

551

print(" " + msg)

552

553

_defaultlogger = norepeatlogger()

553

_defaultlogger = norepeatlogger()

554

555

def getblame(f):

555

def getblame(f):

556

lines = []

556

lines = []

557

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

557

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

558

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

558

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

559

user, rev = start.split()

559

user, rev = start.split()

560

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

560

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

561

return lines

561

return lines

562

563

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

563

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

564

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

564

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

565

"""checks style and portability of a given file

565

"""checks style and portability of a given file

566

567

:f: filepath

567

:f: filepath

568

:logfunc: function used to report error

568

:logfunc: function used to report error

569

logfunc(filename, linenumber, linecontent, errormessage)

569

logfunc(filename, linenumber, linecontent, errormessage)

570

:maxerr: number of error to display before aborting.

570

:maxerr: number of error to display before aborting.

571

Set to false (default) to report all errors

571

Set to false (default) to report all errors

572

573

return True if no error is found, False otherwise.

573

return True if no error is found, False otherwise.

574

"""

574

"""

575

blamecache = None

575

blamecache = None

576

result = True

576

result = True

577

578

try:

578

try:

579

with opentext(f) as fp:

579

with opentext(f) as fp:

580

try:

580

try:

581

pre = post = fp.read()

581

pre = post = fp.read()

582

except UnicodeDecodeError as e:

582

except UnicodeDecodeError as e:

583

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

583

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

584

return result

584

return result

585

except IOError as e:

585

except IOError as e:

586

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

586

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

587

return result

587

return result

588

589

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

589

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

590

post = pre # discard filtering result of previous check

590

post = pre # discard filtering result of previous check

591

if debug:

591

if debug:

592

print(name, f)

592

print(name, f)

593

fc = 0

593

fc = 0

594

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

594

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

595

if debug:

595

if debug:

596

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

596

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

597

name, match, f))

597

name, match, f))

598

continue

598

continue

599

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

599

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

600

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

600

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

601

# no- check- code

601

# no- check- code

602

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

602

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

603

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

603

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

604

# spelling, we write it with the expected spelling from

604

# spelling, we write it with the expected spelling from

605

# tests/test-check-code.t

605

# tests/test-check-code.t

606

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

606

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

607

return "Skip" # skip checking this file

607

return "Skip" # skip checking this file

608

for p, r in filters:

608

for p, r in filters:

609

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

609

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

610

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

610

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

611

if warnings:

611

if warnings:

612

pats = pats[0] + pats[1]

612

pats = pats[0] + pats[1]

613

else:

613

else:

614

pats = pats[0]

614

pats = pats[0]

615

# print post # uncomment to show filtered version

615

# print post # uncomment to show filtered version

616

617

if debug:

617

if debug:

618

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

618

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

619

620

prelines = None

620

prelines = None

621

errors = []

621

errors = []

622

for i, pat in enumerate(pats):

622

for i, pat in enumerate(pats):

623

if len(pat) == 3:

623

if len(pat) == 3:

624

p, msg, ignore = pat

624

p, msg, ignore = pat

625

else:

625

else:

626

p, msg = pat

626

p, msg = pat

627

ignore = None

627

ignore = None

628

if i >= nerrs:

628

if i >= nerrs:

629

msg = "warning: " + msg

629

msg = "warning: " + msg

630

631

pos = 0

631

pos = 0

632

n = 0

632

n = 0

633

for m in p.finditer(post):

633

for m in p.finditer(post):

634

if prelines is None:

634

if prelines is None:

635

prelines = pre.splitlines()

635

prelines = pre.splitlines()

636

postlines = post.splitlines(True)

636

postlines = post.splitlines(True)

637

638

start = m.start()

638

start = m.start()

639

while n < len(postlines):

639

while n < len(postlines):

640

step = len(postlines[n])

640

step = len(postlines[n])

641

if pos + step > start:

641

if pos + step > start:

642

break

642

break

643

pos += step

643

pos += step

644

n += 1

644

n += 1

645

l = prelines[n]

645

l = prelines[n]

646

647

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

647

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

648

if debug:

648

if debug:

649

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

649

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

650

name, f, n))

650

name, f, n))

651

continue

651

continue

652

bd = ""

652

bd = ""

653

if blame:

653

if blame:

654

bd = 'working directory'

654

bd = 'working directory'

655

if not blamecache:

655

if not blamecache:

656

blamecache = getblame(f)

656

blamecache = getblame(f)

657

if n < len(blamecache):

657

if n < len(blamecache):

658

bl, bu, br = blamecache[n]

658

bl, bu, br = blamecache[n]

659

if bl == l:

659

if bl == l:

660

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

660

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

661

662

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

662

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

663

result = False

663

result = False

664

665

errors.sort()

665

errors.sort()

666

for e in errors:

666

for e in errors:

667

logfunc(*e)

667

logfunc(*e)

668

fc += 1

668

fc += 1

669

if maxerr and fc >= maxerr:

669

if maxerr and fc >= maxerr:

670

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

670

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

671

break

671

break

672

673

return result

673

return result

674

675

def main():

675

def main():

676

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

676

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

677

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

677

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

678

help="include warning-level checks")

678

help="include warning-level checks")

679

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

679

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

680

help="max warnings per file")

680

help="max warnings per file")

681

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

681

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

682

help="use annotate to generate blame info")

682

help="use annotate to generate blame info")

683

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

683

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

684

help="show debug information")

684

help="show debug information")

685

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

685

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

686

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

686

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

687

688

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

688

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

689

lineno=True)

689

lineno=True)

690

(options, args) = parser.parse_args()

690

(options, args) = parser.parse_args()

691

692

if len(args) == 0:

692

if len(args) == 0:

693

check = glob.glob("*")

693

check = glob.glob("*")

694

elif args == ['-']:

695

# read file list from stdin

696

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

694

else:

697

else:

695

check = args

698

check = args

696

699

697

_preparepats()

700

_preparepats()

698

701

699

ret = 0

702

ret = 0

700

for f in check:

703

for f in check:

701

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

704

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

702

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

705

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

703

lineno=options.lineno):

706

lineno=options.lineno):

704

ret = 1

707

ret = 1

705

return ret

708

return ret

706

709

707

if __name__ == "__main__":

710

if __name__ == "__main__":

708

sys.exit(main())

711

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'pushd|popd', "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'(^|\|\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, use util.safehasattr(foo, bar) instead'),
                 (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'\.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'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).*(?<!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 = 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())