upstream/mercurial-mirror Commit - r48293:9b1710c5

1

#!/usr/bin/env python3

1

#!/usr/bin/env python3

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

30

if sys.version_info[0] < 3:

30

if sys.version_info[0] < 3:

31

opentext = open

31

opentext = open

32

else:

32

else:

33

34

def opentext(f):

34

def opentext(f):

35

return open(f, encoding='latin1')

35

return open(f, encoding='latin1')

36

37

38

try:

38

try:

39

xrange

39

xrange

40

except NameError:

40

except NameError:

41

xrange = range

41

xrange = range

42

try:

42

try:

43

import re2

43

import re2

44

except ImportError:

44

except ImportError:

45

re2 = None

45

re2 = None

46

47

import testparseutil

47

import testparseutil

48

49

50

def compilere(pat, multiline=False):

50

def compilere(pat, multiline=False):

51

if multiline:

51

if multiline:

52

pat = '(?m)' + pat

52

pat = '(?m)' + pat

53

if re2:

53

if re2:

54

try:

54

try:

55

return re2.compile(pat)

55

return re2.compile(pat)

56

except re2.error:

56

except re2.error:

57

pass

57

pass

58

return re.compile(pat)

58

return re.compile(pat)

59

60

61

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

61

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

62

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

62

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

63

_repquotefixedmap = {

63

_repquotefixedmap = {

64

' ': ' ',

64

' ': ' ',

65

'\n': '\n',

65

'\n': '\n',

66

'.': 'p',

66

'.': 'p',

67

':': 'q',

67

':': 'q',

68

'%': '%',

68

'%': '%',

69

'\\': 'b',

69

'\\': 'b',

70

'*': 'A',

70

'*': 'A',

71

'+': 'P',

71

'+': 'P',

72

'-': 'M',

72

'-': 'M',

73

}

73

}

74

75

76

def _repquoteencodechr(i):

76

def _repquoteencodechr(i):

77

if i > 255:

77

if i > 255:

78

return 'u'

78

return 'u'

79

c = chr(i)

79

c = chr(i)

80

if c in _repquotefixedmap:

80

if c in _repquotefixedmap:

81

return _repquotefixedmap[c]

81

return _repquotefixedmap[c]

82

if c.isalpha():

82

if c.isalpha():

83

return 'x'

83

return 'x'

84

if c.isdigit():

84

if c.isdigit():

85

return 'n'

85

return 'n'

86

return 'o'

86

return 'o'

87

88

89

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

89

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

90

91

92

def repquote(m):

92

def repquote(m):

93

t = m.group('text')

93

t = m.group('text')

94

t = t.translate(_repquotett)

94

t = t.translate(_repquotett)

95

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

95

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

96

97

98

def reppython(m):

98

def reppython(m):

99

comment = m.group('comment')

99

comment = m.group('comment')

100

if comment:

100

if comment:

101

l = len(comment.rstrip())

101

l = len(comment.rstrip())

102

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

102

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

103

return repquote(m)

103

return repquote(m)

104

105

106

def repcomment(m):

106

def repcomment(m):

107

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

107

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

108

109

110

def repccomment(m):

110

def repccomment(m):

111

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

111

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

112

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

112

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

113

114

115

def repcallspaces(m):

115

def repcallspaces(m):

116

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

116

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

117

return m.group(1) + t

117

return m.group(1) + t

118

119

120

def repinclude(m):

120

def repinclude(m):

121

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

121

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

122

123

124

def rephere(m):

124

def rephere(m):

125

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

125

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

126

return m.group(1) + t

126

return m.group(1) + t

127

128

129

testpats = [

129

testpats = [

130

[

130

[

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

(

146

(

147

r'\[[^\]]+==',

147

r'\[[^\]]+==',

148

'[ foo == bar ] is a bashism, use [ foo = bar ] instead',

148

'[ foo == bar ] is a bashism, use [ foo = bar ] instead',

149

),

149

),

150

(

150

(

151

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

151

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

152

"use egrep for extended grep syntax",

152

"use egrep for extended grep syntax",

153

),

153

),

154

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

154

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

155

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

155

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

156

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

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

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

160

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

161

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

161

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

162

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

162

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

163

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

163

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

164

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

164

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

165

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

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

(

170

(

171

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

171

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

172

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

172

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

173

),

173

),

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

(

181

(

182

r'\bsed\b.*[^\\]\\n',

182

r'\bsed\b.*[^\\]\\n',

183

"don't use 'sed ... \\n', use a \\ and a newline",

183

"don't use 'sed ... \\n', use a \\ and a newline",

184

),

184

),

185

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

185

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

186

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

186

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

187

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

187

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

188

(

188

(

189

r'find.*-printf',

189

r'find.*-printf',

190

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

190

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

191

),

191

),

192

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

192

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

193

],

193

],

194

# warnings

194

# warnings

195

[

195

[

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

],

201

],

202

]

202

]

203

204

testfilters = [

204

testfilters = [

205

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

205

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

206

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

206

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

207

]

207

]

208

209

uprefix = r"^ \$ "

209

uprefix = r"^ \$ "

210

utestpats = [

210

utestpats = [

211

[

211

[

212

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

212

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

213

(

213

(

214

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

214

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

215

"use regex test output patterns instead of sed",

215

"use regex test output patterns instead of sed",

216

),

216

),

217

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

217

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

218

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

219

(

218

(

220

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

219

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

221

"explicit exit code checks unnecessary",

220

"explicit exit code checks unnecessary",

222

),

221

),

223

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

222

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

224

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

223

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

225

(

224

(

226

uprefix + r'.*:\.\S*/',

225

uprefix + r'.*:\.\S*/',

227

"x:.y in a path does not work on msys, rewrite "

226

"x:.y in a path does not work on msys, rewrite "

228

"as x://.y, or see `hg log -k msys` for alternatives",

227

"as x://.y, or see `hg log -k msys` for alternatives",

229

r'-\S+:\.|' '# no-msys', # -Rxxx

228

r'-\S+:\.|' '# no-msys', # -Rxxx

230

), # in test-pull.t which is skipped on windows

229

), # in test-pull.t which is skipped on windows

231

(

230

(

232

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

231

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

233

'use $LOCALIP not an explicit loopback address',

232

'use $LOCALIP not an explicit loopback address',

234

),

233

),

235

(

234

(

236

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

235

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

237

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

236

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

238

),

237

),

239

(

238

(

240

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

239

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

241

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

240

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

242

),

241

),

243

(

242

(

244

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

243

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

245

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

244

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

246

),

245

),

247

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

246

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

248

(

247

(

249

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

248

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

250

"glob timezone field in diff output for portability",

249

"glob timezone field in diff output for portability",

251

),

250

),

252

(

251

(

253

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

252

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

254

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

253

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

255

),

254

),

256

(

255

(

257

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

256

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

258

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

257

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

259

),

258

),

260

(

259

(

261

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

260

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

262

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

261

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

263

),

262

),

264

(

263

(

265

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

264

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

266

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

265

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

267

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

266

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

268

),

267

),

269

],

268

],

270

# warnings

269

# warnings

271

[

270

[

272

(

271

(

273

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

272

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

274

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

273

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

275

),

274

),

276

],

275

],

277

]

276

]

278

277

279

# transform plain test rules to unified test's

278

# transform plain test rules to unified test's

280

for i in [0, 1]:

279

for i in [0, 1]:

281

for tp in testpats[i]:

280

for tp in testpats[i]:

282

p = tp[0]

281

p = tp[0]

283

m = tp[1]

282

m = tp[1]

284

if p.startswith('^'):

283

if p.startswith('^'):

285

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

284

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

286

else:

285

else:

287

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

286

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

288

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

287

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

289

288

290

# don't transform the following rules:

289

# don't transform the following rules:

291

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

290

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

292

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

291

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

293

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

292

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

294

293

295

utestfilters = [

294

utestfilters = [

296

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

295

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

297

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

296

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

298

]

297

]

299

298

300

# common patterns to check *.py

299

# common patterns to check *.py

301

commonpypats = [

300

commonpypats = [

302

[

301

[

303

(r'\\$', 'Use () to wrap long lines in Python, not \\'),

302

(r'\\$', 'Use () to wrap long lines in Python, not \\'),

304

(

303

(

305

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

304

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

306

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

305

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

307

),

306

),

308

(

307

(

309

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

308

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

310

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

309

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

311

),

310

),

312

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

311

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

313

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

312

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

314

(

313

(

315

r'\bdict\(.*=',

314

r'\bdict\(.*=',

316

'dict() is different in Py2 and 3 and is slower than {}',

315

'dict() is different in Py2 and 3 and is slower than {}',

317

'dict-from-generator',

316

'dict-from-generator',

318

),

317

),

319

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

318

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

320

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

319

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

321

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

320

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

322

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

321

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

323

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

322

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

324

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

323

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

325

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

324

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

326

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

325

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

327

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

326

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

328

(

327

(

329

(

328

(

330

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

329

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

331

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

330

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

332

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

331

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

333

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

332

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

334

# more lines at the same indent level

333

# more lines at the same indent level

335

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

334

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

336

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

335

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

337

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

336

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

338

),

337

),

339

'omit superfluous pass',

338

'omit superfluous pass',

340

),

339

),

341

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

340

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

342

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

341

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

343

(

342

(

344

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

343

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

345

"don't use camelcase in identifiers",

344

"don't use camelcase in identifiers",

346

r'#.*camelcase-required',

345

r'#.*camelcase-required',

347

),

346

),

348

(

347

(

349

348

350

"linebreak after :",

349

"linebreak after :",

351

),

350

),

352

(

351

(

353

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

352

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

354

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

353

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

355

r'#.*old-style',

354

r'#.*old-style',

356

),

355

),

357

(

356

(

358

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

357

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

359

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

358

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

360

r'#.*old-style',

359

r'#.*old-style',

361

),

360

),

362

(

361

(

363

r'\b(%s)\('

362

r'\b(%s)\('

364

% '|'.join(k for k in keyword.kwlist if k not in ('print', 'exec')),

363

% '|'.join(k for k in keyword.kwlist if k not in ('print', 'exec')),

365

"Python keyword is not a function",

364

"Python keyword is not a function",

366

),

365

),

367

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

366

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

368

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

367

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

369

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

368

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

370

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

369

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

371

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

370

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

372

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

371

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

373

(

372

(

374

r'([$\[][ \t]\S)|(\S[ \t][$\]])',

373

r'([$\[][ \t]\S)|(\S[ \t][$\]])',

375

"gratuitous whitespace in () or []",

374

"gratuitous whitespace in () or []",

376

),

375

),

377

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

376

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

378

(

377

(

379

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

378

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

380

"missing whitespace around operator",

379

"missing whitespace around operator",

381

),

380

),

382

(

381

(

383

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

382

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

384

"missing whitespace around operator",

383

"missing whitespace around operator",

385

),

384

),

386

(

385

(

387

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

386

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

388

"missing whitespace around operator",

387

"missing whitespace around operator",

389

),

388

),

390

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

389

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

391

(

390

(

392

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

391

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

393

"no whitespace around = for named parameters",

392

"no whitespace around = for named parameters",

394

),

393

),

395

(

394

(

396

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

395

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

397

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

396

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

398

),

397

),

399

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

398

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

400

(

399

(

401

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

400

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

402

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

401

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

403

),

402

),

404

(

403

(

405

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

404

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

406

"use True/False for constant Boolean expression",

405

"use True/False for constant Boolean expression",

407

),

406

),

408

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

407

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

409

(

408

(

410

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

409

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

411

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

410

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

412

'instead',

411

'instead',

413

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

412

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

414

),

413

),

415

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

414

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

416

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

415

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

417

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

416

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

418

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

417

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

419

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

418

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

420

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

419

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

421

(

420

(

422

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

421

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

423

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

422

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

424

),

423

),

425

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

424

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

426

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

425

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

427

(

426

(

428

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

427

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

429

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

428

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

430

),

429

),

431

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

430

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

432

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

431

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

433

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

432

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

434

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

433

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

435

(

434

(

436

r'^@(\w*\.)?cachefunc',

435

r'^@(\w*\.)?cachefunc',

437

"module-level @cachefunc is risky, please avoid",

436

"module-level @cachefunc is risky, please avoid",

438

),

437

),

439

(

438

(

440

r'^import Queue',

439

r'^import Queue',

441

"don't use Queue, use pycompat.queue.Queue + "

440

"don't use Queue, use pycompat.queue.Queue + "

442

"pycompat.queue.Empty",

441

"pycompat.queue.Empty",

443

),

442

),

444

(

443

(

445

r'^import cStringIO',

444

r'^import cStringIO',

446

"don't use cStringIO.StringIO, use util.stringio",

445

"don't use cStringIO.StringIO, use util.stringio",

447

),

446

),

448

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

447

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

449

(

448

(

450

r'^import SocketServer',

449

r'^import SocketServer',

451

"don't use SockerServer, use util.socketserver",

450

"don't use SockerServer, use util.socketserver",

452

),

451

),

453

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

452

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

454

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

453

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

455

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

454

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

456

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

455

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

457

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

456

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

458

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

457

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

459

(

458

(

460

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

459

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

461

"use mercurial.policy.importmod instead",

460

"use mercurial.policy.importmod instead",

462

),

461

),

463

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

462

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

464

(

463

(

465

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

464

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

466

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

465

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

467

),

466

),

468

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

467

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

469

],

468

],

470

# warnings

469

# warnings

471

[],

470

[],

472

]

471

]

473

472

474

# patterns to check normal *.py files

473

# patterns to check normal *.py files

475

pypats = [

474

pypats = [

476

[

475

[

477

# Ideally, these should be placed in "commonpypats" for

476

# Ideally, these should be placed in "commonpypats" for

478

# consistency of coding rules in Mercurial source tree.

477

# consistency of coding rules in Mercurial source tree.

479

# But on the other hand, these are not so seriously required for

478

# But on the other hand, these are not so seriously required for

480

# python code fragments embedded in test scripts. Fixing test

479

# python code fragments embedded in test scripts. Fixing test

481

# scripts for these patterns requires many changes, and has less

480

# scripts for these patterns requires many changes, and has less

482

# profit than effort.

481

# profit than effort.

483

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

482

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

484

(r'[\s$](open|file)\([^)]*$\.read\(', "use util.readfile() instead"),

483

(r'[\s$](open|file)\([^)]*$\.read\(', "use util.readfile() instead"),

485

(

484

(

486

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

485

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

487

"use util.writefile() instead",

486

"use util.writefile() instead",

488

),

487

),

489

(

488

(

490

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

489

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

491

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

490

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

492

),

491

),

493

(

492

(

494

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

493

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

495

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

494

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

496

),

495

),

497

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

496

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

498

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

497

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

499

# rules depending on implementation of repquote()

498

# rules depending on implementation of repquote()

500

(

499

(

501

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

500

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

502

'string join across lines with no space',

501

'string join across lines with no space',

503

),

502

),

504

(

503

(

505

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

504

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

506

[ \t\n#]*

505

[ \t\n#]*

507

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

506

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

508

# contains translatable message)

507

# contains translatable message)

509

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

508

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

510

(?# sequence consisting of below might precede translatable message

509

(?# sequence consisting of below might precede translatable message

511

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

510

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

512

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

511

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

513

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

512

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

514

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

513

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

515

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

514

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

516

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

515

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

517

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

516

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

518

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

517

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

519

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

518

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

520

),

519

),

521

]

520

]

522

+ commonpypats[0],

521

+ commonpypats[0],

523

# warnings

522

# warnings

524

[

523

[

525

# rules depending on implementation of repquote()

524

# rules depending on implementation of repquote()

526

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

525

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

527

]

526

]

528

+ commonpypats[1],

527

+ commonpypats[1],

529

]

528

]

530

529

531

# patterns to check *.py for embedded ones in test script

530

# patterns to check *.py for embedded ones in test script

532

embeddedpypats = [

531

embeddedpypats = [

533

[] + commonpypats[0],

532

[] + commonpypats[0],

534

# warnings

533

# warnings

535

[] + commonpypats[1],

534

[] + commonpypats[1],

536

]

535

]

537

536

538

# common filters to convert *.py

537

# common filters to convert *.py

539

commonpyfilters = [

538

commonpyfilters = [

540

(

539

(

541

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

540

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

542

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

541

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

543

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

542

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

544

(?P=quote))""",

543

(?P=quote))""",

545

reppython,

544

reppython,

546

),

545

),

547

]

546

]

548

547

549

# filters to convert normal *.py files

548

# filters to convert normal *.py files

550

pyfilters = [] + commonpyfilters

549

pyfilters = [] + commonpyfilters

551

550

552

# non-filter patterns

551

# non-filter patterns

553

pynfpats = [

552

pynfpats = [

554

[

553

[

555

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

554

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

556

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

555

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

557

(

556

(

558

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

557

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

559

"use pycompat.isdarwin",

558

"use pycompat.isdarwin",

560

),

559

),

561

],

560

],

562

# warnings

561

# warnings

563

[],

562

[],

564

]

563

]

565

564

566

# filters to convert *.py for embedded ones in test script

565

# filters to convert *.py for embedded ones in test script

567

embeddedpyfilters = [] + commonpyfilters

566

embeddedpyfilters = [] + commonpyfilters

568

567

569

# extension non-filter patterns

568

# extension non-filter patterns

570

pyextnfpats = [

569

pyextnfpats = [

571

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

570

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

572

# warnings

571

# warnings

573

[],

572

[],

574

]

573

]

575

574

576

txtfilters = []

575

txtfilters = []

577

576

578

txtpats = [

577

txtpats = [

579

[

578

[

580

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

579

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

581

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

580

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

582

],

581

],

583

[],

582

[],

584

]

583

]

585

584

586

cpats = [

585

cpats = [

587

[

586

[

588

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

587

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

589

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

588

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

590

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

589

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

591

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

590

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

592

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

591

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

593

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

592

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

594

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

593

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

595

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

594

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

596

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

595

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

597

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

596

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

598

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

597

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

599

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

598

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

600

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

599

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

601

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

600

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

602

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

601

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

603

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

602

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

604

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

603

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

605

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

604

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

606

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

605

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

607

# rules depending on implementation of repquote()

606

# rules depending on implementation of repquote()

608

],

607

],

609

# warnings

608

# warnings

610

[

609

[

611

# rules depending on implementation of repquote()

610

# rules depending on implementation of repquote()

612

],

611

],

613

]

612

]

614

613

615

cfilters = [

614

cfilters = [

616

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

615

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

617

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

616

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

618

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

617

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

619

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

618

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

620

]

619

]

621

620

622

inutilpats = [

621

inutilpats = [

623

[

622

[

624

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

623

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

625

],

624

],

626

# warnings

625

# warnings

627

[],

626

[],

628

]

627

]

629

628

630

inrevlogpats = [

629

inrevlogpats = [

631

[

630

[

632

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

631

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

633

],

632

],

634

# warnings

633

# warnings

635

[],

634

[],

636

]

635

]

637

636

638

webtemplatefilters = []

637

webtemplatefilters = []

639

638

640

webtemplatepats = [

639

webtemplatepats = [

641

[],

640

[],

642

[

641

[

643

(

642

(

644

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

643

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

645

'follow desc keyword with either firstline or websub',

644

'follow desc keyword with either firstline or websub',

646

),

645

),

647

],

646

],

648

]

647

]

649

648

650

allfilesfilters = []

649

allfilesfilters = []

651

650

652

allfilespats = [

651

allfilespats = [

653

[

652

[

654

(

653

(

655

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

654

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

656

'use mercurial-scm.org domain URL',

655

'use mercurial-scm.org domain URL',

657

),

656

),

658

(

657

(

659

r'mercurial@selenic\.com',

658

r'mercurial@selenic\.com',

660

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

659

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

661

),

660

),

662

(

661

(

663

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

662

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

664

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

663

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

665

),

664

),

666

],

665

],

667

# warnings

666

# warnings

668

[],

667

[],

669

]

668

]

670

669

671

py3pats = [

670

py3pats = [

672

[

671

[

673

(

672

(

674

r'os\.environ',

673

r'os\.environ',

675

"use encoding.environ instead (py3)",

674

"use encoding.environ instead (py3)",

676

r'#.*re-exports',

675

r'#.*re-exports',

677

),

676

),

678

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

677

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

679

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

678

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

680

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

679

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

681

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

680

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

682

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

681

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

683

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

682

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

684

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

683

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

685

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

684

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

686

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

685

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

687

(r'(?<!pycompat\.)xrange', "use pycompat.xrange instead (py3)"),

686

(r'(?<!pycompat\.)xrange', "use pycompat.xrange instead (py3)"),

688

],

687

],

689

# warnings

688

# warnings

690

[],

689

[],

691

]

690

]

692

691

693

checks = [

692

checks = [

694

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

693

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

695

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

694

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

696

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

695

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

697

(

696

(

698

'python 3',

697

'python 3',

699

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

698

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

700

'',

699

'',

701

pyfilters,

700

pyfilters,

702

py3pats,

701

py3pats,

703

),

702

),

704

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

703

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

705

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

704

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

706

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

705

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

707

(

706

(

708

'layering violation repo in revlog',

707

'layering violation repo in revlog',

709

r'mercurial/revlog\.py',

708

r'mercurial/revlog\.py',

710

'',

709

'',

711

pyfilters,

710

pyfilters,

712

inrevlogpats,

711

inrevlogpats,

713

),

712

),

714

(

713

(

715

'layering violation ui in util',

714

'layering violation ui in util',

716

r'mercurial/util\.py',

715

r'mercurial/util\.py',

717

'',

716

'',

718

pyfilters,

717

pyfilters,

719

inutilpats,

718

inutilpats,

720

),

719

),

721

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

720

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

722

(

721

(

723

'web template',

722

'web template',

724

r'mercurial/templates/.*\.tmpl',

723

r'mercurial/templates/.*\.tmpl',

725

'',

724

'',

726

webtemplatefilters,

725

webtemplatefilters,

727

webtemplatepats,

726

webtemplatepats,

728

),

727

),

729

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

728

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

730

]

729

]

731

730

732

# (desc,

731

# (desc,

733

# func to pick up embedded code fragments,

732

# func to pick up embedded code fragments,

734

# list of patterns to convert target files

733

# list of patterns to convert target files

735

# list of patterns to detect errors/warnings)

734

# list of patterns to detect errors/warnings)

736

embeddedchecks = [

735

embeddedchecks = [

737

(

736

(

738

'embedded python',

737

'embedded python',

739

testparseutil.pyembedded,

738

testparseutil.pyembedded,

740

embeddedpyfilters,

739

embeddedpyfilters,

741

embeddedpypats,

740

embeddedpypats,

742

)

741

)

743

]

742

]

744

743

745

744

746

def _preparepats():

745

def _preparepats():

747

def preparefailandwarn(failandwarn):

746

def preparefailandwarn(failandwarn):

748

for pats in failandwarn:

747

for pats in failandwarn:

749

for i, pseq in enumerate(pats):

748

for i, pseq in enumerate(pats):

750

# fix-up regexes for multi-line searches

749

# fix-up regexes for multi-line searches

751

p = pseq[0]

750

p = pseq[0]

752

# \s doesn't match \n (done in two steps)

751

# \s doesn't match \n (done in two steps)

753

# first, we replace \s that appears in a set already

752

# first, we replace \s that appears in a set already

754

p = re.sub(r'\[\\s', r'[ \\t', p)

753

p = re.sub(r'\[\\s', r'[ \\t', p)

755

# now we replace other \s instances.

754

# now we replace other \s instances.

756

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

755

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

757

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

756

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

758

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

757

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

759

758

760

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

759

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

761

760

762

def preparefilters(filters):

761

def preparefilters(filters):

763

for i, flt in enumerate(filters):

762

for i, flt in enumerate(filters):

764

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

763

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

765

764

766

for cs in (checks, embeddedchecks):

765

for cs in (checks, embeddedchecks):

767

for c in cs:

766

for c in cs:

768

failandwarn = c[-1]

767

failandwarn = c[-1]

769

preparefailandwarn(failandwarn)

768

preparefailandwarn(failandwarn)

770

769

771

filters = c[-2]

770

filters = c[-2]

772

preparefilters(filters)

771

preparefilters(filters)

773

772

774

773

775

class norepeatlogger(object):

774

class norepeatlogger(object):

776

def __init__(self):

775

def __init__(self):

777

self._lastseen = None

776

self._lastseen = None

778

777

779

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

778

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

780

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

779

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

781

780

782

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

781

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

783

of multiple errors.

782

of multiple errors.

784

783

785

:fname: filename

784

:fname: filename

786

:lineno: line number

785

:lineno: line number

787

:line: actual content of the line

786

:line: actual content of the line

788

:msg: error message

787

:msg: error message

789

"""

788

"""

790

msgid = fname, lineno, line

789

msgid = fname, lineno, line

791

if msgid != self._lastseen:

790

if msgid != self._lastseen:

792

if blame:

791

if blame:

793

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

792

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

794

else:

793

else:

795

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

794

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

796

print(" > %s" % line)

795

print(" > %s" % line)

797

self._lastseen = msgid

796

self._lastseen = msgid

798

print(" " + msg)

797

print(" " + msg)

799

798

800

799

801

_defaultlogger = norepeatlogger()

800

_defaultlogger = norepeatlogger()

802

801

803

802

804

def getblame(f):

803

def getblame(f):

805

lines = []

804

lines = []

806

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

805

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

807

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

806

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

808

user, rev = start.split()

807

user, rev = start.split()

809

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

808

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

810

return lines

809

return lines

811

810

812

811

813

def checkfile(

812

def checkfile(

814

f,

813

f,

815

logfunc=_defaultlogger.log,

814

logfunc=_defaultlogger.log,

816

maxerr=None,

815

maxerr=None,

817

warnings=False,

816

warnings=False,

818

blame=False,

817

blame=False,

819

debug=False,

818

debug=False,

820

lineno=True,

819

lineno=True,

821

):

820

):

822

"""checks style and portability of a given file

821

"""checks style and portability of a given file

823

822

824

:f: filepath

823

:f: filepath

825

:logfunc: function used to report error

824

:logfunc: function used to report error

826

logfunc(filename, linenumber, linecontent, errormessage)

825

logfunc(filename, linenumber, linecontent, errormessage)

827

:maxerr: number of error to display before aborting.

826

:maxerr: number of error to display before aborting.

828

Set to false (default) to report all errors

827

Set to false (default) to report all errors

829

828

830

return True if no error is found, False otherwise.

829

return True if no error is found, False otherwise.

831

"""

830

"""

832

result = True

831

result = True

833

832

834

try:

833

try:

835

with opentext(f) as fp:

834

with opentext(f) as fp:

836

try:

835

try:

837

pre = fp.read()

836

pre = fp.read()

838

except UnicodeDecodeError as e:

837

except UnicodeDecodeError as e:

839

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

838

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

840

return result

839

return result

841

except IOError as e:

840

except IOError as e:

842

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

841

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

843

return result

842

return result

844

843

845

# context information shared while single checkfile() invocation

844

# context information shared while single checkfile() invocation

846

context = {'blamecache': None}

845

context = {'blamecache': None}

847

846

848

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

847

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

849

if debug:

848

if debug:

850

print(name, f)

849

print(name, f)

851

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

850

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

852

if debug:

851

if debug:

853

print(

852

print(

854

"Skipping %s for %s it doesn't match %s" % (name, match, f)

853

"Skipping %s for %s it doesn't match %s" % (name, match, f)

855

)

854

)

856

continue

855

continue

857

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

856

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

858

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

857

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

859

# no- check- code

858

# no- check- code

860

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

859

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

861

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

860

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

862

# spelling, we write it with the expected spelling from

861

# spelling, we write it with the expected spelling from

863

# tests/test-check-code.t

862

# tests/test-check-code.t

864

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

863

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

865

return "Skip" # skip checking this file

864

return "Skip" # skip checking this file

866

865

867

fc = _checkfiledata(

866

fc = _checkfiledata(

868

name,

867

name,

869

f,

868

f,

870

pre,

869

pre,

871

filters,

870

filters,

872

pats,

871

pats,

873

context,

872

context,

874

logfunc,

873

logfunc,

875

maxerr,

874

maxerr,

876

warnings,

875

warnings,

877

blame,

876

blame,

878

debug,

877

debug,

879

lineno,

878

lineno,

880

)

879

)

881

if fc:

880

if fc:

882

result = False

881

result = False

883

882

884

if f.endswith('.t') and "no-" "check-code" not in pre:

883

if f.endswith('.t') and "no-" "check-code" not in pre:

885

if debug:

884

if debug:

886

print("Checking embedded code in %s" % f)

885

print("Checking embedded code in %s" % f)

887

886

888

prelines = pre.splitlines()

887

prelines = pre.splitlines()

889

embeddederros = []

888

embeddederros = []

890

for name, embedded, filters, pats in embeddedchecks:

889

for name, embedded, filters, pats in embeddedchecks:

891

# "reset curmax at each repetition" treats maxerr as "max

890

# "reset curmax at each repetition" treats maxerr as "max

892

# nubmer of errors in an actual file per entry of

891

# nubmer of errors in an actual file per entry of

893

# (embedded)checks"

892

# (embedded)checks"

894

curmaxerr = maxerr

893

curmaxerr = maxerr

895

894

896

for found in embedded(f, prelines, embeddederros):

895

for found in embedded(f, prelines, embeddederros):

897

filename, starts, ends, code = found

896

filename, starts, ends, code = found

898

fc = _checkfiledata(

897

fc = _checkfiledata(

899

name,

898

name,

900

f,

899

f,

901

code,

900

code,

902

filters,

901

filters,

903

pats,

902

pats,

904

context,

903

context,

905

logfunc,

904

logfunc,

906

curmaxerr,

905

curmaxerr,

907

warnings,

906

warnings,

908

blame,

907

blame,

909

debug,

908

debug,

910

lineno,

909

lineno,

911

offset=starts - 1,

910

offset=starts - 1,

912

)

911

)

913

if fc:

912

if fc:

914

result = False

913

result = False

915

if curmaxerr:

914

if curmaxerr:

916

if fc >= curmaxerr:

915

if fc >= curmaxerr:

917

break

916

break

918

curmaxerr -= fc

917

curmaxerr -= fc

919

918

920

return result

919

return result

921

920

922

921

923

def _checkfiledata(

922

def _checkfiledata(

924

name,

923

name,

925

f,

924

f,

926

filedata,

925

filedata,

927

filters,

926

filters,

928

pats,

927

pats,

929

context,

928

context,

930

logfunc,

929

logfunc,

931

maxerr,

930

maxerr,

932

warnings,

931

warnings,

933

blame,

932

blame,

934

debug,

933

debug,

935

lineno,

934

lineno,

936

offset=None,

935

offset=None,

937

):

936

):

938

"""Execute actual error check for file data

937

"""Execute actual error check for file data

939

938

940

:name: of the checking category

939

:name: of the checking category

941

:f: filepath

940

:f: filepath

942

:filedata: content of a file

941

:filedata: content of a file

943

:filters: to be applied before checking

942

:filters: to be applied before checking

944

:pats: to detect errors

943

:pats: to detect errors

945

:context: a dict of information shared while single checkfile() invocation

944

:context: a dict of information shared while single checkfile() invocation

946

Valid keys: 'blamecache'.

945

Valid keys: 'blamecache'.

947

:logfunc: function used to report error

946

:logfunc: function used to report error

948

logfunc(filename, linenumber, linecontent, errormessage)

947

logfunc(filename, linenumber, linecontent, errormessage)

949

:maxerr: number of error to display before aborting, or False to

948

:maxerr: number of error to display before aborting, or False to

950

report all errors

949

report all errors

951

:warnings: whether warning level checks should be applied

950

:warnings: whether warning level checks should be applied

952

:blame: whether blame information should be displayed at error reporting

951

:blame: whether blame information should be displayed at error reporting

953

:debug: whether debug information should be displayed

952

:debug: whether debug information should be displayed

954

:lineno: whether lineno should be displayed at error reporting

953

:lineno: whether lineno should be displayed at error reporting

955

:offset: line number offset of 'filedata' in 'f' for checking

954

:offset: line number offset of 'filedata' in 'f' for checking

956

an embedded code fragment, or None (offset=0 is different

955

an embedded code fragment, or None (offset=0 is different

957

from offset=None)

956

from offset=None)

958

957

959

returns number of detected errors.

958

returns number of detected errors.

960

"""

959

"""

961

blamecache = context['blamecache']

960

blamecache = context['blamecache']

962

if offset is None:

961

if offset is None:

963

lineoffset = 0

962

lineoffset = 0

964

else:

963

else:

965

lineoffset = offset

964

lineoffset = offset

966

965

967

fc = 0

966

fc = 0

968

pre = post = filedata

967

pre = post = filedata

969

968

970

if True: # TODO: get rid of this redundant 'if' block

969

if True: # TODO: get rid of this redundant 'if' block

971

for p, r in filters:

970

for p, r in filters:

972

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

971

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

973

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

972

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

974

if warnings:

973

if warnings:

975

pats = pats[0] + pats[1]

974

pats = pats[0] + pats[1]

976

else:

975

else:

977

pats = pats[0]

976

pats = pats[0]

978

# print post # uncomment to show filtered version

977

# print post # uncomment to show filtered version

979

978

980

if debug:

979

if debug:

981

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

980

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

982

981

983

prelines = None

982

prelines = None

984

errors = []

983

errors = []

985

for i, pat in enumerate(pats):

984

for i, pat in enumerate(pats):

986

if len(pat) == 3:

985

if len(pat) == 3:

987

p, msg, ignore = pat

986

p, msg, ignore = pat

988

else:

987

else:

989

p, msg = pat

988

p, msg = pat

990

ignore = None

989

ignore = None

991

if i >= nerrs:

990

if i >= nerrs:

992

msg = "warning: " + msg

991

msg = "warning: " + msg

993

992

994

pos = 0

993

pos = 0

995

n = 0

994

n = 0

996

for m in p.finditer(post):

995

for m in p.finditer(post):

997

if prelines is None:

996

if prelines is None:

998

prelines = pre.splitlines()

997

prelines = pre.splitlines()

999

postlines = post.splitlines(True)

998

postlines = post.splitlines(True)

1000

999

1001

start = m.start()

1000

start = m.start()

1002

while n < len(postlines):

1001

while n < len(postlines):

1003

step = len(postlines[n])

1002

step = len(postlines[n])

1004

if pos + step > start:

1003

if pos + step > start:

1005

break

1004

break

1006

pos += step

1005

pos += step

1007

n += 1

1006

n += 1

1008

l = prelines[n]

1007

l = prelines[n]

1009

1008

1010

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

1009

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

1011

if debug:

1010

if debug:

1012

print(

1011

print(

1013

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

1012

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

1014

% (name, f, (n + lineoffset))

1013

% (name, f, (n + lineoffset))

1015

)

1014

)

1016

continue

1015

continue

1017

bd = ""

1016

bd = ""

1018

if blame:

1017

if blame:

1019

bd = 'working directory'

1018

bd = 'working directory'

1020

if blamecache is None:

1019

if blamecache is None:

1021

blamecache = getblame(f)

1020

blamecache = getblame(f)

1022

context['blamecache'] = blamecache

1021

context['blamecache'] = blamecache

1023

if (n + lineoffset) < len(blamecache):

1022

if (n + lineoffset) < len(blamecache):

1024

bl, bu, br = blamecache[(n + lineoffset)]

1023

bl, bu, br = blamecache[(n + lineoffset)]

1025

if offset is None and bl == l:

1024

if offset is None and bl == l:

1026

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

1025

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

1027

elif offset is not None and bl.endswith(l):

1026

elif offset is not None and bl.endswith(l):

1028

# "offset is not None" means "checking

1027

# "offset is not None" means "checking

1029

# embedded code fragment". In this case,

1028

# embedded code fragment". In this case,

1030

# "l" does not have information about the

1029

# "l" does not have information about the

1031

# beginning of an *original* line in the

1030

# beginning of an *original* line in the

1032

# file (e.g. ' > ').

1031

# file (e.g. ' > ').

1033

# Therefore, use "str.endswith()", and

1032

# Therefore, use "str.endswith()", and

1034

# show "maybe" for a little loose

1033

# show "maybe" for a little loose

1035

# examination.

1034

# examination.

1036

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

1035

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

1037

1036

1038

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

1037

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

1039

1038

1040

errors.sort()

1039

errors.sort()

1041

for e in errors:

1040

for e in errors:

1042

logfunc(*e)

1041

logfunc(*e)

1043

fc += 1

1042

fc += 1

1044

if maxerr and fc >= maxerr:

1043

if maxerr and fc >= maxerr:

1045

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

1044

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

1046

break

1045

break

1047

1046

1048

return fc

1047

return fc

1049

1048

1050

1049

1051

def main():

1050

def main():

1052

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

1051

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

1053

parser.add_option(

1052

parser.add_option(

1054

"-w",

1053

"-w",

1055

"--warnings",

1054

"--warnings",

1056

action="store_true",

1055

action="store_true",

1057

help="include warning-level checks",

1056

help="include warning-level checks",

1058

)

1057

)

1059

parser.add_option(

1058

parser.add_option(

1060

"-p", "--per-file", type="int", help="max warnings per file"

1059

"-p", "--per-file", type="int", help="max warnings per file"

1061

)

1060

)

1062

parser.add_option(

1061

parser.add_option(

1063

"-b",

1062

"-b",

1064

"--blame",

1063

"--blame",

1065

action="store_true",

1064

action="store_true",

1066

help="use annotate to generate blame info",

1065

help="use annotate to generate blame info",

1067

)

1066

)

1068

parser.add_option(

1067

parser.add_option(

1069

"", "--debug", action="store_true", help="show debug information"

1068

"", "--debug", action="store_true", help="show debug information"

1070

)

1069

)

1071

parser.add_option(

1070

parser.add_option(

1072

"",

1071

"",

1073

"--nolineno",

1072

"--nolineno",

1074

action="store_false",

1073

action="store_false",

1075

dest='lineno',

1074

dest='lineno',

1076

help="don't show line numbers",

1075

help="don't show line numbers",

1077

)

1076

)

1078

1077

1079

parser.set_defaults(

1078

parser.set_defaults(

1080

per_file=15, warnings=False, blame=False, debug=False, lineno=True

1079

per_file=15, warnings=False, blame=False, debug=False, lineno=True

1081

)

1080

)

1082

(options, args) = parser.parse_args()

1081

(options, args) = parser.parse_args()

1083

1082

1084

if len(args) == 0:

1083

if len(args) == 0:

1085

check = glob.glob("*")

1084

check = glob.glob("*")

1086

elif args == ['-']:

1085

elif args == ['-']:

1087

# read file list from stdin

1086

# read file list from stdin

1088

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

1087

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

1089

else:

1088

else:

1090

check = args

1089

check = args

1091

1090

1092

_preparepats()

1091

_preparepats()

1093

1092

1094

ret = 0

1093

ret = 0

1095

for f in check:

1094

for f in check:

1096

if not checkfile(

1095

if not checkfile(

1097

f,

1096

f,

1098

maxerr=options.per_file,

1097

maxerr=options.per_file,

1099

warnings=options.warnings,

1098

warnings=options.warnings,

1100

blame=options.blame,

1099

blame=options.blame,

1101

debug=options.debug,

1100

debug=options.debug,

1102

lineno=options.lineno,

1101

lineno=options.lineno,

1103

):

1102

):

1104

ret = 1

1103

ret = 1

1105

return ret

1104

return ret

1106

1105

1107

1106

1108

if __name__ == "__main__":

1107

if __name__ == "__main__":

1109

sys.exit(main())

1108

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 python3
             #
             # check-code - a style and portability checker for Mercurial
             #
             # Copyright 2010 Olivia Mackall <olivia@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='latin1')
             try:
                 xrange
             except NameError:
                 xrange = range
             try:
                 import re2
             except ImportError:
                 re2 = None
             import testparseutil
             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'\bls\b.*-\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'rm -rf \*', "don't use naked rm -rf, target a directory"),
                     (
                         r'\[[^\]]+==',
                         '[ foo == bar ] is a bashism, use [ foo = bar ] instead',
                     ),
                     (
                         r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                         "use egrep for extended grep syntax",
                     ),
                     (r'(^|\|\s*)e?grep .*\\S', "don't use \\S in regular expression"),
                     (r'(?<!!)/bin/', "don't use explicit paths for tools"),
                     (r'#!.*/bash', "don't use bash in shebang, use sh"),
                     (r'[^\n]\Z', "no trailing newline"),
                     (r'export .*=', "don't export and assign at once"),
                     (r'^source\b', "don't use 'source', use '.'"),
                     (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                     (r'\bls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
                     (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
                     (r'^stop\(\)', "don't use 'stop' as a shell function name"),
                     (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
                     (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
                     (r'^alias\b.*=', "don't use alias, use a function"),
                     (r'if\s*!', "don't use '!' to negate exit status"),
                     (r'/dev/u?random', "don't use entropy, use /dev/zero"),
                     (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
                     (
                         r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
                         "put a backslash-escaped newline after sed 'i' command",
                     ),
                     (r'^diff *-\w*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
                     (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
                     (r'[\s="`\']python\s(?!bindings)', "don't use 'python', use '$PYTHON'"),
                     (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
                     (r'\butil\.Abort\b', "directly use error.Abort"),
                     (r'\|&', "don't use |&, use 2>&1"),
                     (r'\w =  +\w', "only one space after = allowed"),
                     (
                         r'\bsed\b.*[^\\]\\n',
                         "don't use 'sed ... \\n', use a \\ and a newline",
                     ),
                     (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),
                     (r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),
                     (r'grep.* -[ABC]', "don't use grep's context flags"),
                     (
                         r'find.*-printf',
                         "don't use 'find -printf', it doesn't exist on BSD find(1)",
                     ),
                     (r'\$RANDOM ', "don't use bash-only $RANDOM to generate random values"),
                 ],
                 # warnings
                 [
                     (r'^function', "don't use 'function', use old style"),
                     (r'^diff.*-\w*N', "don't use 'diff -N'"),
                     (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
                     (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
                     (r'kill (`|\$\()', "don't use kill, use killdaemons.py"),
                 ],
             ]
             testfilters = [
                 (r"( *)(#([^!][^\n]*\S)?)", repcomment),
                 (r"<<(\S+)((.|\n)*?\n\1)", rephere),
             ]
             uprefix = r"^  \$ "
             utestpats = [
                 [
                     (r'^(\S.*||  [$>] \S.*)[ \t]\n', "trailing whitespace on non-output"),
                     (
                         uprefix + r'.*\|\s*sed[^|>\n]*\n',
                         "use regex test output patterns instead of sed",
                     ),
                     (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
-                    (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
                     (
                         uprefix + r'.*\|\| echo.*(fail|error)',
                         "explicit exit code checks unnecessary",
                     ),
                     (uprefix + r'set -e', "don't use set -e"),
                     (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
                     (
                         uprefix + r'.*:\.\S*/',
                         "x:.y in a path does not work on msys, rewrite "
                         "as x://.y, or see `hg log -k msys` for alternatives",
                         r'-\S+:\.|' '# no-msys',  # -Rxxx
                     ),  # in test-pull.t which is skipped on windows
                     (
                         r'^  [^$>].*27\.0\.0\.1',
                         'use $LOCALIP not an explicit loopback address',
                     ),
                     (
                         r'^  (?![>$] ).*\$LOCALIP.*[^)]$',
                         'mark $LOCALIP output lines with (glob) to help tests in BSD jails',
                     ),
                     (
                         r'^  (cat|find): .*: \$ENOENT\$',
                         'use test -f to test for file existence',
                     ),
                     (
                         r'^  diff -[^ -]*p',
                         "don't use (external) diff with -p for portability",
                     ),
                     (r' readlink ', 'use readlink.py instead of readlink'),
                     (
                         r'^  [-+][-+][-+] .* [-+]0000 \(glob\)',
                         "glob timezone field in diff output for portability",
                     ),
                     (
                         r'^  @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',
                         "use '@@ -N* +N,n @@ (glob)' style chunk header for portability",
                     ),
                     (
                         r'^  @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',
                         "use '@@ -N,n +N* @@ (glob)' style chunk header for portability",
                     ),
                     (
                         r'^  @@ -[0-9]+ [+][0-9]+ @@',
                         "use '@@ -N* +N* @@ (glob)' style chunk header for portability",
                     ),
                     (
                         uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'
                         r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',
                         "use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)",
                     ),
                 ],
                 # warnings
                 [
                     (
                         r'^  (?!.*\$LOCALIP)[^*?/\n]* \(glob\)$',
                         "glob match with no glob string (?, *, /, and $LOCALIP)",
                     ),
                 ],
             ]
             # transform plain test rules to unified test's
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith('^'):
                         p = "^  [$>] (%s)" % p[1:]
                     else:
                         p = "^  [$>] .*(%s)" % p
                     utestpats[i].append((p, m) + tp[2:])
             # don't transform the following rules:
             # "  > \t" and "  \t" should be allowed in unified tests
             testpats[0].append((r'^( *)\t', "don't use tabs to indent"))
             utestpats[0].append((r'^( ?)\t', "don't use tabs to indent"))
             utestfilters = [
                 (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
                 (r"( +)(#([^!][^\n]*\S)?)", repcomment),
             ]
             # common patterns to check *.py
             commonpypats = [
                 [
                     (r'\\$', 'Use () to wrap long lines in Python, not \\'),
                     (
                         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'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                     (
                         (
                             # a line ending with a colon, potentially with trailing comments
                             r':([ \t]*#[^\n]*)?\n'
                             # one that is not a pass and not only a comment
                             r'(?P<indent>[ \t]+)[^#][^\n]+\n'
                             # more lines at the same indent level
                             r'((?P=indent)[^\n]+\n)*'
                             # a pass at the same indent level, which is bogus
                             r'(?P=indent)pass[ \t\n#]'
                         ),
                         'omit superfluous pass',
                     ),
                     (r'[^\n]\Z', "no trailing newline"),
                     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
                     (
                         r'^\s+(self\.)?[A-Za-z][a-z0-9]+[A-Z]\w* = ',
                         "don't use camelcase in identifiers",
                         r'#.*camelcase-required',
                     ),
                     (
                         r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                         "linebreak after :",
                     ),
                     (
                         r'class\s[^( \n]+:',
                         "old-style class, use class foo(object)",
                         r'#.*old-style',
                     ),
                     (
                         r'class\s[^( \n]+\(\):',
                         "class foo() creates old style object, use class foo(object)",
                         r'#.*old-style',
                     ),
                     (
                         r'\b(%s)\('
                         % '|'.join(k for k in keyword.kwlist if k not in ('print', 'exec')),
                         "Python keyword is not a function",
                     ),
                     #    (r'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'([\(\[][ \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 [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                         "don't use old-style two-argument raise, use Exception(message)",
                     ),
                     (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                     (
                         r' [=!]=\s+(True|False|None)',
                         "comparison with singleton, use 'is' or 'is not' instead",
                     ),
                     (
                         r'^\s*(while|if) [01]:',
                         "use True/False for constant Boolean expression",
                     ),
                     (r'^\s*if False(:| +and)', 'Remove code instead of using `if False`'),
                     (
                         r'(?:(?<!def)\s+|\()hasattr\(',
                         'hasattr(foo, bar) is broken on py2, use util.safehasattr(foo, bar) '
                         'instead',
                         r'#.*hasattr-py3-only',
                     ),
                     (r'opener\([^)]*\).read\(', "use opener.read() instead"),
                     (r'opener\([^)]*\).write\(', "use opener.write() instead"),
                     (r'(?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'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 pycompat.queue.Queue + "
                         "pycompat.queue.Empty",
                     ),
                     (
                         r'^import cStringIO',
                         "don't use cStringIO.StringIO, use util.stringio",
                     ),
                     (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
                     (
                         r'^import SocketServer',
                         "don't use SockerServer, use util.socketserver",
                     ),
                     (r'^import urlparse', "don't use urlparse, use util.urlreq"),
                     (r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),
                     (r'^import cPickle', "don't use cPickle, use util.pickle"),
                     (r'^import pickle', "don't use pickle, use util.pickle"),
                     (r'^import httplib', "don't use httplib, use util.httplib"),
                     (r'^import BaseHTTPServer', "use util.httpserver instead"),
                     (
                         r'^(from|import) mercurial\.(cext|pure|cffi)',
                         "use mercurial.policy.importmod instead",
                     ),
                     (r'\.next\(\)', "don't use .next(), use next(...)"),
                     (
                         r'([a-z]*).revision\(\1\.node\(',
                         "don't convert rev to node before passing to revision(nodeorrev)",
                     ),
                     (r'platform\.system\(\)', "don't use platform.system(), use pycompat"),
                 ],
                 # warnings
                 [],
             ]
             # patterns to check normal *.py files
             pypats = [
                 [
                     # Ideally, these should be placed in "commonpypats" for
                     # consistency of coding rules in Mercurial source tree.
                     # But on the other hand, these are not so seriously required for
                     # python code fragments embedded in test scripts. Fixing test
                     # scripts for these patterns requires many changes, and has less
                     # profit than effort.
                     (r'raise Exception', "don't raise generic exceptions"),
                     (r'[\s\(](open|file)\([^)]*\)\.read\(', "use util.readfile() instead"),
                     (
                         r'[\s\(](open|file)\([^)]*\)\.write\(',
                         "use util.writefile() instead",
                     ),
                     (
                         r'^[\s\(]*(open(er)?|file)\([^)]*\)(?!\.close\(\))',
                         "always assign an opened file to a variable, and close it afterwards",
                     ),
                     (
                         r'[\s\(](open|file)\([^)]*\)\.(?!close\(\))',
                         "always assign an opened file to a variable, and close it afterwards",
                     ),
                     (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                     (r'^import atexit', "don't use atexit, use ui.atexit"),
                     # 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)
                      b?((['"]|\'\'\'|""")[ \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)",
                     ),
                 ]
                 + commonpypats[0],
                 # warnings
                 [
                     # rules depending on implementation of repquote()
                     (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
                 ]
                 + commonpypats[1],
             ]
             # patterns to check *.py for embedded ones in test script
             embeddedpypats = [
                 [] + commonpypats[0],
                 # warnings
                 [] + commonpypats[1],
             ]
             # common filters to convert *.py
             commonpyfilters = [
                 (
                     r"""(?msx)(?P<comment>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""",
                     reppython,
                 ),
             ]
             # filters to convert normal *.py files
             pyfilters = [] + commonpyfilters
             # non-filter patterns
             pynfpats = [
                 [
                     (r'pycompat\.osname\s*[=!]=\s*[\'"]nt[\'"]', "use pycompat.iswindows"),
                     (r'pycompat\.osname\s*[=!]=\s*[\'"]posix[\'"]', "use pycompat.isposix"),
                     (
                         r'pycompat\.sysplatform\s*[!=]=\s*[\'"]darwin[\'"]',
                         "use pycompat.isdarwin",
                     ),
                 ],
                 # warnings
                 [],
             ]
             # filters to convert *.py for embedded ones in test script
             embeddedpyfilters = [] + commonpyfilters
             # extension non-filter patterns
             pyextnfpats = [
                 [(r'^"""\n?[A-Z]', "don't capitalize docstring title")],
                 # warnings
                 [],
             ]
             txtfilters = []
             txtpats = [
                 [
                     (r'\s$', 'trailing whitespace'),
                     ('.. note::[ \n][^\n]', 'add two newlines after note::'),
                 ],
                 [],
             ]
             cpats = [
                 [
                     (r'//', "don't use //-style comments"),
                     (r'\S\t', "don't use tabs except for indent"),
                     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
                     (r'(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 encoding.getcwd instead (py3)", r'#.*re-exports'),
                     (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"),
                     (r'(?<!pycompat\.)xrange', "use pycompat.xrange instead (py3)"),
                 ],
                 # warnings
                 [],
             ]
             checks = [
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', [], pynfpats),
                 ('python', r'.*hgext.*\.py$', '', [], pyextnfpats),
                 (
                     'python 3',
                     r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',
                     '',
                     pyfilters,
                     py3pats,
                 ),
                 ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),
                 ('c', r'.*\.[ch]$', '', cfilters, cpats),
                 ('unified test', r'.*\.t$', '', utestfilters, utestpats),
                 (
                     'layering violation repo in revlog',
                     r'mercurial/revlog\.py',
                     '',
                     pyfilters,
                     inrevlogpats,
                 ),
                 (
                     'layering violation ui in util',
                     r'mercurial/util\.py',
                     '',
                     pyfilters,
                     inutilpats,
                 ),
                 ('txt', r'.*\.txt$', '', txtfilters, txtpats),
                 (
                     'web template',
                     r'mercurial/templates/.*\.tmpl',
                     '',
                     webtemplatefilters,
                     webtemplatepats,
                 ),
                 ('all except for .po', r'.*(?<!\.po)$', '', allfilesfilters, allfilespats),
             ]
             # (desc,
             #  func to pick up embedded code fragments,
             #  list of patterns to convert target files
             #  list of patterns to detect errors/warnings)
             embeddedchecks = [
                 (
                     'embedded python',
                     testparseutil.pyembedded,
                     embeddedpyfilters,
                     embeddedpypats,
                 )
             ]
             def _preparepats():
                 def preparefailandwarn(failandwarn):
                     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 (done in two steps)
                             # first, we replace \s that appears in a set already
                             p = re.sub(r'\[\\s', r'[ \\t', p)
                             # now we replace other \s instances.
                             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:]
                 def preparefilters(filters):
                     for i, flt in enumerate(filters):
                         filters[i] = re.compile(flt[0]), flt[1]
                 for cs in (checks, embeddedchecks):
                     for c in cs:
                         failandwarn = c[-1]
                         preparefailandwarn(failandwarn)
                         filters = c[-2]
                         preparefilters(filters)
             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.
                 """
                 result = True
                 try:
                     with opentext(f) as fp:
                         try:
                             pre = 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
                 # context information shared while single checkfile() invocation
                 context = {'blamecache': None}
                 for name, match, magic, filters, pats in checks:
                     if debug:
                         print(name, f)
                     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
                     fc = _checkfiledata(
                         name,
                         f,
                         pre,
                         filters,
                         pats,
                         context,
                         logfunc,
                         maxerr,
                         warnings,
                         blame,
                         debug,
                         lineno,
                     )
                     if fc:
                         result = False
                 if f.endswith('.t') and "no-" "check-code" not in pre:
                     if debug:
                         print("Checking embedded code in %s" % f)
                     prelines = pre.splitlines()
                     embeddederros = []
                     for name, embedded, filters, pats in embeddedchecks:
                         # "reset curmax at each repetition" treats maxerr as "max
                         # nubmer of errors in an actual file per entry of
                         # (embedded)checks"
                         curmaxerr = maxerr
                         for found in embedded(f, prelines, embeddederros):
                             filename, starts, ends, code = found
                             fc = _checkfiledata(
                                 name,
                                 f,
                                 code,
                                 filters,
                                 pats,
                                 context,
                                 logfunc,
                                 curmaxerr,
                                 warnings,
                                 blame,
                                 debug,
                                 lineno,
                                 offset=starts - 1,
                             )
                             if fc:
                                 result = False
                                 if curmaxerr:
                                     if fc >= curmaxerr:
                                         break
                                     curmaxerr -= fc
                 return result
             def _checkfiledata(
                 name,
                 f,
                 filedata,
                 filters,
                 pats,
                 context,
                 logfunc,
                 maxerr,
                 warnings,
                 blame,
                 debug,
                 lineno,
                 offset=None,
             ):
                 """Execute actual error check for file data
                 :name: of the checking category
                 :f: filepath
                 :filedata: content of a file
                 :filters: to be applied before checking
                 :pats: to detect errors
                 :context: a dict of information shared while single checkfile() invocation
                           Valid keys: 'blamecache'.
                 :logfunc: function used to report error
                           logfunc(filename, linenumber, linecontent, errormessage)
                 :maxerr: number of error to display before aborting, or False to
                          report all errors
                 :warnings: whether warning level checks should be applied
                 :blame: whether blame information should be displayed at error reporting
                 :debug: whether debug information should be displayed
                 :lineno: whether lineno should be displayed at error reporting
                 :offset: line number offset of 'filedata' in 'f' for checking
                          an embedded code fragment, or None (offset=0 is different
                          from offset=None)
                 returns number of detected errors.
                 """
                 blamecache = context['blamecache']
                 if offset is None:
                     lineoffset = 0
                 else:
                     lineoffset = offset
                 fc = 0
                 pre = post = filedata
                 if True:  # TODO: get rid of this redundant 'if' block
                     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 + lineoffset))
                                     )
                                 continue
                             bd = ""
                             if blame:
                                 bd = 'working directory'
                                 if blamecache is None:
                                     blamecache = getblame(f)
                                     context['blamecache'] = blamecache
                                 if (n + lineoffset) < len(blamecache):
                                     bl, bu, br = blamecache[(n + lineoffset)]
                                     if offset is None and bl == l:
                                         bd = '%s@%s' % (bu, br)
                                     elif offset is not None and bl.endswith(l):
                                         # "offset is not None" means "checking
                                         # embedded code fragment". In this case,
                                         # "l" does not have information about the
                                         # beginning of an *original* line in the
                                         # file (e.g. '  > ').
                                         # Therefore, use "str.endswith()", and
                                         # show "maybe" for a little loose
                                         # examination.
                                         bd = '%s@%s, maybe' % (bu, br)
                             errors.append((f, lineno and (n + lineoffset + 1), l, msg, bd))
                     errors.sort()
                     for e in errors:
                         logfunc(*e)
                         fc += 1
                         if maxerr and fc >= maxerr:
                             print(" (too many errors, giving up)")
                             break
                 return fc
             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())