upstream/mercurial-mirror Commit - r48435:752109dc

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

(

218

(

219

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

219

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

220

"explicit exit code checks unnecessary",

220

"explicit exit code checks unnecessary",

221

),

221

),

222

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

222

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

223

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

223

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

224

(

224

(

225

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

225

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

226

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

226

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

227

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

227

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

228

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

228

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

229

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

229

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

230

(

230

(

231

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

231

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

232

'use $LOCALIP not an explicit loopback address',

232

'use $LOCALIP not an explicit loopback address',

233

),

233

),

234

(

234

(

235

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

235

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

236

'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',

237

),

237

),

238

(

238

(

239

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

239

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

240

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

240

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

241

),

241

),

242

(

242

(

243

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

243

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

244

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

244

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

245

),

245

),

246

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

246

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

247

(

247

(

248

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

248

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

249

"glob timezone field in diff output for portability",

249

"glob timezone field in diff output for portability",

250

),

250

),

251

(

251

(

252

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

252

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

253

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

253

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

254

),

254

),

255

(

255

(

256

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

256

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

257

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

257

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

258

),

258

),

259

(

259

(

260

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

260

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

261

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

261

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

262

),

262

),

263

(

263

(

264

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

264

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

265

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

265

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

266

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

266

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

267

),

267

),

268

],

268

],

269

# warnings

269

# warnings

270

[

270

[

271

(

271

(

272

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

272

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

273

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

273

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

274

),

274

),

275

],

275

],

276

]

276

]

277

278

# transform plain test rules to unified test's

278

# transform plain test rules to unified test's

279

for i in [0, 1]:

279

for i in [0, 1]:

280

for tp in testpats[i]:

280

for tp in testpats[i]:

281

p = tp[0]

281

p = tp[0]

282

m = tp[1]

282

m = tp[1]

283

if p.startswith('^'):

283

if p.startswith('^'):

284

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

284

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

285

else:

285

else:

286

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

286

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

287

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

287

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

288

289

# don't transform the following rules:

289

# don't transform the following rules:

290

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

290

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

291

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

291

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

292

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

292

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

293

294

utestfilters = [

294

utestfilters = [

295

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

295

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

296

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

296

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

297

]

297

]

298

299

# common patterns to check *.py

299

# common patterns to check *.py

300

commonpypats = [

300

commonpypats = [

301

[

301

[

302

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

302

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

303

(

303

(

304

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

304

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

305

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

305

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

306

),

306

),

307

(

307

(

308

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

308

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

309

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

309

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

310

),

310

),

311

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

311

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

312

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

312

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

313

(

313

(

314

r'\bdict\(.*=',

314

r'\bdict\(.*=',

315

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

315

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

316

'dict-from-generator',

316

'dict-from-generator',

317

),

317

),

318

(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+"),

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

(

327

(

328

(

328

(

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

# more lines at the same indent level

333

# more lines at the same indent level

334

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

334

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

335

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

335

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

336

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

336

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

337

),

337

),

338

'omit superfluous pass',

338

'omit superfluous pass',

339

),

339

),

340

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

340

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

341

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

341

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

342

(

342

(

343

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* = ',

344

"don't use camelcase in identifiers",

344

"don't use camelcase in identifiers",

345

r'#.*camelcase-required',

345

r'#.*camelcase-required',

346

),

346

),

347

(

347

(

348

348

349

"linebreak after :",

349

"linebreak after :",

350

),

350

),

351

(

351

(

352

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

352

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

353

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

353

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

354

r'#.*old-style',

354

r'#.*old-style',

355

),

355

),

356

(

356

(

357

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

357

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

358

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

358

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

359

r'#.*old-style',

359

r'#.*old-style',

360

),

360

),

361

(

361

(

362

r'\b(%s)\('

362

r'\b(%s)\('

363

% '|'.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')),

364

"Python keyword is not a function",

364

"Python keyword is not a function",

365

),

365

),

366

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

366

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

367

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

367

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

368

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

368

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

369

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

369

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

370

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

370

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

371

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

371

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

372

(

372

(

373

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

373

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

374

"gratuitous whitespace in () or []",

374

"gratuitous whitespace in () or []",

375

),

375

),

376

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

376

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

377

(

377

(

378

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

378

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

379

"missing whitespace around operator",

379

"missing whitespace around operator",

380

),

380

),

381

(

381

(

382

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

382

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

383

"missing whitespace around operator",

383

"missing whitespace around operator",

384

),

384

),

385

(

385

(

386

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

386

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

387

"missing whitespace around operator",

387

"missing whitespace around operator",

388

),

388

),

389

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

389

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

390

(

390

(

391

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

391

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

392

"no whitespace around = for named parameters",

392

"no whitespace around = for named parameters",

393

),

393

),

394

(

394

(

395

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

395

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

396

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

396

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

397

),

397

),

398

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

398

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

399

(

399

(

400

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

400

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

401

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

401

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

402

),

402

),

403

(

403

(

404

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

404

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

405

"use True/False for constant Boolean expression",

405

"use True/False for constant Boolean expression",

406

),

406

),

407

(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`'),

408

(

408

(

409

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

409

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

410

'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) '

411

'instead',

411

'instead',

412

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

412

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

413

),

413

),

414

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

414

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

415

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

415

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

416

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

416

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

417

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

417

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

418

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

418

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

419

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

419

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

420

(

420

(

421

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

421

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

422

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

422

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

423

),

423

),

424

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

424

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

425

(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"),

426

(

426

(

427

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

427

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

428

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

428

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

429

),

429

),

430

(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"'),

431

# 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

432

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

432

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

433

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

433

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

434

(

434

(

435

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

435

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

436

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

436

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

437

),

437

),

438

(

438

(

439

r'^import Queue',

439

r'^import Queue',

440

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

440

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

441

"pycompat.queue.Empty",

441

"pycompat.queue.Empty",

442

),

442

),

443

(

443

(

444

r'^import cStringIO',

444

r'^import cStringIO',

445

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

445

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

446

),

446

),

447

(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"),

448

(

448

(

449

r'^import SocketServer',

449

r'^import SocketServer',

450

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

450

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

451

),

451

),

452

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

452

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

453

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

453

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

454

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

454

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

455

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

455

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

456

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

456

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

457

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

457

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

458

(

458

(

459

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

459

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

460

"use mercurial.policy.importmod instead",

460

"use mercurial.policy.importmod instead",

461

),

461

),

462

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

462

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

463

(

463

(

464

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

464

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

465

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

465

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

466

),

466

),

467

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

467

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

468

],

468

],

469

# warnings

469

# warnings

470

[],

470

[],

471

]

471

]

472

473

# patterns to check normal *.py files

473

# patterns to check normal *.py files

474

pypats = [

474

pypats = [

475

[

475

[

476

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

476

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

477

# consistency of coding rules in Mercurial source tree.

477

# consistency of coding rules in Mercurial source tree.

478

# 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

479

# python code fragments embedded in test scripts. Fixing test

479

# python code fragments embedded in test scripts. Fixing test

480

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

480

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

481

# profit than effort.

481

# profit than effort.

482

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

482

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

483

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

483

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

484

(

484

(

485

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

485

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

486

"use util.writefile() instead",

486

"use util.writefile() instead",

487

),

487

),

488

(

488

(

489

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

489

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

490

"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",

491

),

491

),

492

(

492

(

493

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

493

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

494

"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",

495

),

495

),

496

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

496

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

497

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

497

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

498

# rules depending on implementation of repquote()

498

# rules depending on implementation of repquote()

499

(

499

(

500

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

500

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

501

'string join across lines with no space',

501

'string join across lines with no space',

502

),

502

),

503

(

503

(

504

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

504

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

505

[ \t\n#]*

505

[ \t\n#]*

506

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

506

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

507

# contains translatable message)

507

# contains translatable message)

508

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

508

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

509

(?# sequence consisting of below might precede translatable message

509

(?# sequence consisting of below might precede translatable message

510

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

510

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

511

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

511

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

512

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

512

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

513

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

513

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

514

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

514

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

515

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

515

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

516

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

516

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

517

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

517

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

518

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

518

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

519

),

519

),

520

]

520

]

521

+ commonpypats[0],

521

+ commonpypats[0],

522

# warnings

522

# warnings

523

[

523

[

524

# rules depending on implementation of repquote()

524

# rules depending on implementation of repquote()

525

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

525

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

526

]

526

]

527

+ commonpypats[1],

527

+ commonpypats[1],

528

]

528

]

529

530

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

530

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

531

embeddedpypats = [

531

embeddedpypats = [

532

[] + commonpypats[0],

532

[] + commonpypats[0],

533

# warnings

533

# warnings

534

[] + commonpypats[1],

534

[] + commonpypats[1],

535

]

535

]

536

537

# common filters to convert *.py

537

# common filters to convert *.py

538

commonpyfilters = [

538

commonpyfilters = [

539

(

539

(

540

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

540

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

541

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

541

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

542

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

542

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

543

(?P=quote))""",

543

(?P=quote))""",

544

reppython,

544

reppython,

545

),

545

),

546

]

546

]

547

548

# pattern only for mercurial and extensions

549

core_py_pats = [

550

[

551

# Windows tend to get confused about capitalization of the drive letter

552

#

553

# see mercurial.windows.abspath for details

554

(

555

r'os\.path\.abspath',

556

"use util.abspath instead (windows)",

557

r'#.*re-exports',

558

),

559

],

560

# warnings

561

[],

562

]

563

548

# filters to convert normal *.py files

564

# filters to convert normal *.py files

549

pyfilters = [] + commonpyfilters

565

pyfilters = [] + commonpyfilters

550

566

551

# non-filter patterns

567

# non-filter patterns

552

pynfpats = [

568

pynfpats = [

553

[

569

[

554

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

570

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

555

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

571

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

556

(

572

(

557

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

573

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

558

"use pycompat.isdarwin",

574

"use pycompat.isdarwin",

559

),

575

),

560

],

576

],

561

# warnings

577

# warnings

562

[],

578

[],

563

]

579

]

564

580

565

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

581

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

566

embeddedpyfilters = [] + commonpyfilters

582

embeddedpyfilters = [] + commonpyfilters

567

583

568

# extension non-filter patterns

584

# extension non-filter patterns

569

pyextnfpats = [

585

pyextnfpats = [

570

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

586

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

571

# warnings

587

# warnings

572

[],

588

[],

573

]

589

]

574

590

575

txtfilters = []

591

txtfilters = []

576

592

577

txtpats = [

593

txtpats = [

578

[

594

[

579

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

595

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

580

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

596

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

581

],

597

],

582

[],

598

[],

583

]

599

]

584

600

585

cpats = [

601

cpats = [

586

[

602

[

587

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

603

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

588

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

604

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

589

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

605

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

590

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

606

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

591

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

607

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

592

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

608

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

593

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

609

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

594

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

610

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

595

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

611

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

596

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

612

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

597

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

613

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

598

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

614

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

599

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

615

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

600

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

616

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

601

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

617

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

602

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

618

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

603

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

619

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

604

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

620

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

605

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

621

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

606

# rules depending on implementation of repquote()

622

# rules depending on implementation of repquote()

607

],

623

],

608

# warnings

624

# warnings

609

[

625

[

610

# rules depending on implementation of repquote()

626

# rules depending on implementation of repquote()

611

],

627

],

612

]

628

]

613

629

614

cfilters = [

630

cfilters = [

615

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

631

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

616

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

632

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

617

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

633

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

618

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

634

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

619

]

635

]

620

636

621

inutilpats = [

637

inutilpats = [

622

[

638

[

623

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

639

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

624

],

640

],

625

# warnings

641

# warnings

626

[],

642

[],

627

]

643

]

628

644

629

inrevlogpats = [

645

inrevlogpats = [

630

[

646

[

631

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

647

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

632

],

648

],

633

# warnings

649

# warnings

634

[],

650

[],

635

]

651

]

636

652

637

webtemplatefilters = []

653

webtemplatefilters = []

638

654

639

webtemplatepats = [

655

webtemplatepats = [

640

[],

656

[],

641

[

657

[

642

(

658

(

643

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

659

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

644

'follow desc keyword with either firstline or websub',

660

'follow desc keyword with either firstline or websub',

645

),

661

),

646

],

662

],

647

]

663

]

648

664

649

allfilesfilters = []

665

allfilesfilters = []

650

666

651

allfilespats = [

667

allfilespats = [

652

[

668

[

653

(

669

(

654

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

670

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

655

'use mercurial-scm.org domain URL',

671

'use mercurial-scm.org domain URL',

656

),

672

),

657

(

673

(

658

r'mercurial@selenic\.com',

674

r'mercurial@selenic\.com',

659

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

675

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

660

),

676

),

661

(

677

(

662

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

678

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

663

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

679

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

664

),

680

),

665

],

681

],

666

# warnings

682

# warnings

667

[],

683

[],

668

]

684

]

669

685

670

py3pats = [

686

py3pats = [

671

[

687

[

672

(

688

(

673

r'os\.environ',

689

r'os\.environ',

674

"use encoding.environ instead (py3)",

690

"use encoding.environ instead (py3)",

675

r'#.*re-exports',

691

r'#.*re-exports',

676

),

692

),

677

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

693

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

678

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

694

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

679

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

695

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

680

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

696

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

681

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

697

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

682

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

698

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

683

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

699

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

684

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

700

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

685

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

701

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

686

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

702

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

687

],

703

],

688

# warnings

704

# warnings

689

[],

705

[],

690

]

706

]

691

707

692

checks = [

708

checks = [

693

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

709

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

694

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

710

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

695

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

711

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

696

(

712

(

697

'python 3',

713

'python 3',

698

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

714

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

699

'',

715

'',

700

pyfilters,

716

pyfilters,

701

py3pats,

717

py3pats,

702

),

718

),

719

(

720

'core files',

721

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

722

'',

723

pyfilters,

724

core_py_pats,

725

),

703

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

726

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

704

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

727

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

705

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

728

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

706

(

729

(

707

'layering violation repo in revlog',

730

'layering violation repo in revlog',

708

r'mercurial/revlog\.py',

731

r'mercurial/revlog\.py',

709

'',

732

'',

710

pyfilters,

733

pyfilters,

711

inrevlogpats,

734

inrevlogpats,

712

),

735

),

713

(

736

(

714

'layering violation ui in util',

737

'layering violation ui in util',

715

r'mercurial/util\.py',

738

r'mercurial/util\.py',

716

'',

739

'',

717

pyfilters,

740

pyfilters,

718

inutilpats,

741

inutilpats,

719

),

742

),

720

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

743

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

721

(

744

(

722

'web template',

745

'web template',

723

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

746

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

724

'',

747

'',

725

webtemplatefilters,

748

webtemplatefilters,

726

webtemplatepats,

749

webtemplatepats,

727

),

750

),

728

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

751

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

729

]

752

]

730

753

731

# (desc,

754

# (desc,

732

# func to pick up embedded code fragments,

755

# func to pick up embedded code fragments,

733

# list of patterns to convert target files

756

# list of patterns to convert target files

734

# list of patterns to detect errors/warnings)

757

# list of patterns to detect errors/warnings)

735

embeddedchecks = [

758

embeddedchecks = [

736

(

759

(

737

'embedded python',

760

'embedded python',

738

testparseutil.pyembedded,

761

testparseutil.pyembedded,

739

embeddedpyfilters,

762

embeddedpyfilters,

740

embeddedpypats,

763

embeddedpypats,

741

)

764

)

742

]

765

]

743

766

744

767

745

def _preparepats():

768

def _preparepats():

746

def preparefailandwarn(failandwarn):

769

def preparefailandwarn(failandwarn):

747

for pats in failandwarn:

770

for pats in failandwarn:

748

for i, pseq in enumerate(pats):

771

for i, pseq in enumerate(pats):

749

# fix-up regexes for multi-line searches

772

# fix-up regexes for multi-line searches

750

p = pseq[0]

773

p = pseq[0]

751

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

774

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

752

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

775

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

753

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

776

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

754

# now we replace other \s instances.

777

# now we replace other \s instances.

755

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

778

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

756

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

779

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

757

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

780

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

758

781

759

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

782

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

760

783

761

def preparefilters(filters):

784

def preparefilters(filters):

762

for i, flt in enumerate(filters):

785

for i, flt in enumerate(filters):

763

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

786

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

764

787

765

for cs in (checks, embeddedchecks):

788

for cs in (checks, embeddedchecks):

766

for c in cs:

789

for c in cs:

767

failandwarn = c[-1]

790

failandwarn = c[-1]

768

preparefailandwarn(failandwarn)

791

preparefailandwarn(failandwarn)

769

792

770

filters = c[-2]

793

filters = c[-2]

771

preparefilters(filters)

794

preparefilters(filters)

772

795

773

796

774

class norepeatlogger(object):

797

class norepeatlogger(object):

775

def __init__(self):

798

def __init__(self):

776

self._lastseen = None

799

self._lastseen = None

777

800

778

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

801

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

779

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

802

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

780

803

781

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

804

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

782

of multiple errors.

805

of multiple errors.

783

806

784

:fname: filename

807

:fname: filename

785

:lineno: line number

808

:lineno: line number

786

:line: actual content of the line

809

:line: actual content of the line

787

:msg: error message

810

:msg: error message

788

"""

811

"""

789

msgid = fname, lineno, line

812

msgid = fname, lineno, line

790

if msgid != self._lastseen:

813

if msgid != self._lastseen:

791

if blame:

814

if blame:

792

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

815

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

793

else:

816

else:

794

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

817

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

795

print(" > %s" % line)

818

print(" > %s" % line)

796

self._lastseen = msgid

819

self._lastseen = msgid

797

print(" " + msg)

820

print(" " + msg)

798

821

799

822

800

_defaultlogger = norepeatlogger()

823

_defaultlogger = norepeatlogger()

801

824

802

825

803

def getblame(f):

826

def getblame(f):

804

lines = []

827

lines = []

805

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

828

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

806

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

829

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

807

user, rev = start.split()

830

user, rev = start.split()

808

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

831

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

809

return lines

832

return lines

810

833

811

834

812

def checkfile(

835

def checkfile(

813

f,

836

f,

814

logfunc=_defaultlogger.log,

837

logfunc=_defaultlogger.log,

815

maxerr=None,

838

maxerr=None,

816

warnings=False,

839

warnings=False,

817

blame=False,

840

blame=False,

818

debug=False,

841

debug=False,

819

lineno=True,

842

lineno=True,

820

):

843

):

821

"""checks style and portability of a given file

844

"""checks style and portability of a given file

822

845

823

:f: filepath

846

:f: filepath

824

:logfunc: function used to report error

847

:logfunc: function used to report error

825

logfunc(filename, linenumber, linecontent, errormessage)

848

logfunc(filename, linenumber, linecontent, errormessage)

826

:maxerr: number of error to display before aborting.

849

:maxerr: number of error to display before aborting.

827

Set to false (default) to report all errors

850

Set to false (default) to report all errors

828

851

829

return True if no error is found, False otherwise.

852

return True if no error is found, False otherwise.

830

"""

853

"""

831

result = True

854

result = True

832

855

833

try:

856

try:

834

with opentext(f) as fp:

857

with opentext(f) as fp:

835

try:

858

try:

836

pre = fp.read()

859

pre = fp.read()

837

except UnicodeDecodeError as e:

860

except UnicodeDecodeError as e:

838

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

861

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

839

return result

862

return result

840

except IOError as e:

863

except IOError as e:

841

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

864

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

842

return result

865

return result

843

866

844

# context information shared while single checkfile() invocation

867

# context information shared while single checkfile() invocation

845

context = {'blamecache': None}

868

context = {'blamecache': None}

846

869

847

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

870

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

848

if debug:

871

if debug:

849

print(name, f)

872

print(name, f)

850

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

873

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

851

if debug:

874

if debug:

852

print(

875

print(

853

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

876

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

854

)

877

)

855

continue

878

continue

856

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

879

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

857

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

880

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

858

# no- check- code

881

# no- check- code

859

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

882

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

860

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

883

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

861

# spelling, we write it with the expected spelling from

884

# spelling, we write it with the expected spelling from

862

# tests/test-check-code.t

885

# tests/test-check-code.t

863

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

886

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

864

return "Skip" # skip checking this file

887

return "Skip" # skip checking this file

865

888

866

fc = _checkfiledata(

889

fc = _checkfiledata(

867

name,

890

name,

868

f,

891

f,

869

pre,

892

pre,

870

filters,

893

filters,

871

pats,

894

pats,

872

context,

895

context,

873

logfunc,

896

logfunc,

874

maxerr,

897

maxerr,

875

warnings,

898

warnings,

876

blame,

899

blame,

877

debug,

900

debug,

878

lineno,

901

lineno,

879

)

902

)

880

if fc:

903

if fc:

881

result = False

904

result = False

882

905

883

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

906

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

884

if debug:

907

if debug:

885

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

908

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

886

909

887

prelines = pre.splitlines()

910

prelines = pre.splitlines()

888

embeddederros = []

911

embeddederros = []

889

for name, embedded, filters, pats in embeddedchecks:

912

for name, embedded, filters, pats in embeddedchecks:

890

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

913

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

891

# nubmer of errors in an actual file per entry of

914

# nubmer of errors in an actual file per entry of

892

# (embedded)checks"

915

# (embedded)checks"

893

curmaxerr = maxerr

916

curmaxerr = maxerr

894

917

895

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

918

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

896

filename, starts, ends, code = found

919

filename, starts, ends, code = found

897

fc = _checkfiledata(

920

fc = _checkfiledata(

898

name,

921

name,

899

f,

922

f,

900

code,

923

code,

901

filters,

924

filters,

902

pats,

925

pats,

903

context,

926

context,

904

logfunc,

927

logfunc,

905

curmaxerr,

928

curmaxerr,

906

warnings,

929

warnings,

907

blame,

930

blame,

908

debug,

931

debug,

909

lineno,

932

lineno,

910

offset=starts - 1,

933

offset=starts - 1,

911

)

934

)

912

if fc:

935

if fc:

913

result = False

936

result = False

914

if curmaxerr:

937

if curmaxerr:

915

if fc >= curmaxerr:

938

if fc >= curmaxerr:

916

break

939

break

917

curmaxerr -= fc

940

curmaxerr -= fc

918

941

919

return result

942

return result

920

943

921

944

922

def _checkfiledata(

945

def _checkfiledata(

923

name,

946

name,

924

f,

947

f,

925

filedata,

948

filedata,

926

filters,

949

filters,

927

pats,

950

pats,

928

context,

951

context,

929

logfunc,

952

logfunc,

930

maxerr,

953

maxerr,

931

warnings,

954

warnings,

932

blame,

955

blame,

933

debug,

956

debug,

934

lineno,

957

lineno,

935

offset=None,

958

offset=None,

936

):

959

):

937

"""Execute actual error check for file data

960

"""Execute actual error check for file data

938

961

939

:name: of the checking category

962

:name: of the checking category

940

:f: filepath

963

:f: filepath

941

:filedata: content of a file

964

:filedata: content of a file

942

:filters: to be applied before checking

965

:filters: to be applied before checking

943

:pats: to detect errors

966

:pats: to detect errors

944

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

967

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

945

Valid keys: 'blamecache'.

968

Valid keys: 'blamecache'.

946

:logfunc: function used to report error

969

:logfunc: function used to report error

947

logfunc(filename, linenumber, linecontent, errormessage)

970

logfunc(filename, linenumber, linecontent, errormessage)

948

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

971

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

949

report all errors

972

report all errors

950

:warnings: whether warning level checks should be applied

973

:warnings: whether warning level checks should be applied

951

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

974

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

952

:debug: whether debug information should be displayed

975

:debug: whether debug information should be displayed

953

:lineno: whether lineno should be displayed at error reporting

976

:lineno: whether lineno should be displayed at error reporting

954

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

977

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

955

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

978

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

956

from offset=None)

979

from offset=None)

957

980

958

returns number of detected errors.

981

returns number of detected errors.

959

"""

982

"""

960

blamecache = context['blamecache']

983

blamecache = context['blamecache']

961

if offset is None:

984

if offset is None:

962

lineoffset = 0

985

lineoffset = 0

963

else:

986

else:

964

lineoffset = offset

987

lineoffset = offset

965

988

966

fc = 0

989

fc = 0

967

pre = post = filedata

990

pre = post = filedata

968

991

969

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

992

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

970

for p, r in filters:

993

for p, r in filters:

971

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

994

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

972

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

995

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

973

if warnings:

996

if warnings:

974

pats = pats[0] + pats[1]

997

pats = pats[0] + pats[1]

975

else:

998

else:

976

pats = pats[0]

999

pats = pats[0]

977

# print post # uncomment to show filtered version

1000

# print post # uncomment to show filtered version

978

1001

979

if debug:

1002

if debug:

980

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

1003

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

981

1004

982

prelines = None

1005

prelines = None

983

errors = []

1006

errors = []

984

for i, pat in enumerate(pats):

1007

for i, pat in enumerate(pats):

985

if len(pat) == 3:

1008

if len(pat) == 3:

986

p, msg, ignore = pat

1009

p, msg, ignore = pat

987

else:

1010

else:

988

p, msg = pat

1011

p, msg = pat

989

ignore = None

1012

ignore = None

990

if i >= nerrs:

1013

if i >= nerrs:

991

msg = "warning: " + msg

1014

msg = "warning: " + msg

992

1015

993

pos = 0

1016

pos = 0

994

n = 0

1017

n = 0

995

for m in p.finditer(post):

1018

for m in p.finditer(post):

996

if prelines is None:

1019

if prelines is None:

997

prelines = pre.splitlines()

1020

prelines = pre.splitlines()

998

postlines = post.splitlines(True)

1021

postlines = post.splitlines(True)

999

1022

1000

start = m.start()

1023

start = m.start()

1001

while n < len(postlines):

1024

while n < len(postlines):

1002

step = len(postlines[n])

1025

step = len(postlines[n])

1003

if pos + step > start:

1026

if pos + step > start:

1004

break

1027

break

1005

pos += step

1028

pos += step

1006

n += 1

1029

n += 1

1007

l = prelines[n]

1030

l = prelines[n]

1008

1031

1009

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

1032

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

1010

if debug:

1033

if debug:

1011

print(

1034

print(

1012

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

1035

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

1013

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

1036

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

1014

)

1037

)

1015

continue

1038

continue

1016

bd = ""

1039

bd = ""

1017

if blame:

1040

if blame:

1018

bd = 'working directory'

1041

bd = 'working directory'

1019

if blamecache is None:

1042

if blamecache is None:

1020

blamecache = getblame(f)

1043

blamecache = getblame(f)

1021

context['blamecache'] = blamecache

1044

context['blamecache'] = blamecache

1022

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

1045

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

1023

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

1046

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

1024

if offset is None and bl == l:

1047

if offset is None and bl == l:

1025

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

1048

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

1026

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

1049

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

1027

# "offset is not None" means "checking

1050

# "offset is not None" means "checking

1028

# embedded code fragment". In this case,

1051

# embedded code fragment". In this case,

1029

# "l" does not have information about the

1052

# "l" does not have information about the

1030

# beginning of an *original* line in the

1053

# beginning of an *original* line in the

1031

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

1054

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

1032

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

1055

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

1033

# show "maybe" for a little loose

1056

# show "maybe" for a little loose

1034

# examination.

1057

# examination.

1035

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

1058

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

1036

1059

1037

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

1060

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

1038

1061

1039

errors.sort()

1062

errors.sort()

1040

for e in errors:

1063

for e in errors:

1041

logfunc(*e)

1064

logfunc(*e)

1042

fc += 1

1065

fc += 1

1043

if maxerr and fc >= maxerr:

1066

if maxerr and fc >= maxerr:

1044

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

1067

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

1045

break

1068

break

1046

1069

1047

return fc

1070

return fc

1048

1071

1049

1072

1050

def main():

1073

def main():

1051

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

1074

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

1052

parser.add_option(

1075

parser.add_option(

1053

"-w",

1076

"-w",

1054

"--warnings",

1077

"--warnings",

1055

action="store_true",

1078

action="store_true",

1056

help="include warning-level checks",

1079

help="include warning-level checks",

1057

)

1080

)

1058

parser.add_option(

1081

parser.add_option(

1059

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

1082

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

1060

)

1083

)

1061

parser.add_option(

1084

parser.add_option(

1062

"-b",

1085

"-b",

1063

"--blame",

1086

"--blame",

1064

action="store_true",

1087

action="store_true",

1065

help="use annotate to generate blame info",

1088

help="use annotate to generate blame info",

1066

)

1089

)

1067

parser.add_option(

1090

parser.add_option(

1068

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

1091

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

1069

)

1092

)

1070

parser.add_option(

1093

parser.add_option(

1071

"",

1094

"",

1072

"--nolineno",

1095

"--nolineno",

1073

action="store_false",

1096

action="store_false",

1074

dest='lineno',

1097

dest='lineno',

1075

help="don't show line numbers",

1098

help="don't show line numbers",

1076

)

1099

)

1077

1100

1078

parser.set_defaults(

1101

parser.set_defaults(

1079

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

1102

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

1080

)

1103

)

1081

(options, args) = parser.parse_args()

1104

(options, args) = parser.parse_args()

1082

1105

1083

if len(args) == 0:

1106

if len(args) == 0:

1084

check = glob.glob("*")

1107

check = glob.glob("*")

1085

elif args == ['-']:

1108

elif args == ['-']:

1086

# read file list from stdin

1109

# read file list from stdin

1087

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

1110

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

1088

else:

1111

else:

1089

check = args

1112

check = args

1090

1113

1091

_preparepats()

1114

_preparepats()

1092

1115

1093

ret = 0

1116

ret = 0

1094

for f in check:

1117

for f in check:

1095

if not checkfile(

1118

if not checkfile(

1096

f,

1119

f,

1097

maxerr=options.per_file,

1120

maxerr=options.per_file,

1098

warnings=options.warnings,

1121

warnings=options.warnings,

1099

blame=options.blame,

1122

blame=options.blame,

1100

debug=options.debug,

1123

debug=options.debug,

1101

lineno=options.lineno,

1124

lineno=options.lineno,

1102

):

1125

):

1103

ret = 1

1126

ret = 1

1104

return ret

1127

return ret

1105

1128

1106

1129

1107

if __name__ == "__main__":

1130

if __name__ == "__main__":

1108

sys.exit(main())

1131

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.*||  [$>] \S.*)[ \t]\n', "trailing whitespace on non-output"),
                     (
                         uprefix + r'.*\|\s*sed[^|>\n]*\n',
                         "use regex test output patterns instead of sed",
                     ),
                     (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
                     (
                         uprefix + r'.*\|\| echo.*(fail|error)',
                         "explicit exit code checks unnecessary",
                     ),
                     (uprefix + r'set -e', "don't use set -e"),
                     (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
                     (
                         uprefix + r'.*:\.\S*/',
                         "x:.y in a path does not work on msys, rewrite "
                         "as x://.y, or see `hg log -k msys` for alternatives",
                         r'-\S+:\.|' '# no-msys',  # -Rxxx
                     ),  # in test-pull.t which is skipped on windows
                     (
                         r'^  [^$>].*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>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""",
                     reppython,
                 ),
             ]
+            # pattern only for mercurial and extensions
+            core_py_pats = [
+                [
+                    # Windows tend to get confused about capitalization of the drive letter
+                    #
+                    # see mercurial.windows.abspath for details
+                    (
+                        r'os\.path\.abspath',
+                        "use util.abspath instead (windows)",
+                        r'#.*re-exports',
+                    ),
+                ],
+                # warnings
+                [],
+            ]
             # filters to convert normal *.py files
             pyfilters = [] + commonpyfilters
             # non-filter patterns
             pynfpats = [
                 [
                     (r'pycompat\.osname\s*[=!]=\s*[\'"]nt[\'"]', "use pycompat.iswindows"),
                     (r'pycompat\.osname\s*[=!]=\s*[\'"]posix[\'"]', "use pycompat.isposix"),
                     (
                         r'pycompat\.sysplatform\s*[!=]=\s*[\'"]darwin[\'"]',
                         "use pycompat.isdarwin",
                     ),
                 ],
                 # warnings
                 [],
             ]
             # filters to convert *.py for embedded ones in test script
             embeddedpyfilters = [] + commonpyfilters
             # extension non-filter patterns
             pyextnfpats = [
                 [(r'^"""\n?[A-Z]', "don't capitalize docstring title")],
                 # warnings
                 [],
             ]
             txtfilters = []
             txtpats = [
                 [
                     (r'\s$', '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$', '', [], pyextnfpats),
                 (
                     'python 3',
                     r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',
                     '',
                     pyfilters,
                     py3pats,
                 ),
+                (
+                    'core files',
+                    r'.*(hgext|mercurial)/(?!demandimport|policy|pycompat).*\.py',
+                    '',
+                    pyfilters,
+                    core_py_pats,
+                ),
                 ('test script', r'(.*/)?test-[^.~]*$', '', 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())