upstream/mercurial-mirror Commit - r51619:65f949da

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

import glob

22

import glob

23

import keyword

23

import keyword

24

import optparse

24

import optparse

25

import os

25

import os

26

import re

26

import re

27

import sys

27

import sys

28

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

33

def opentext(f):

33

def opentext(f):

34

return open(f, encoding='latin1')

34

return open(f, encoding='latin1')

35

36

37

try:

37

try:

38

xrange

38

xrange

39

except NameError:

39

except NameError:

40

xrange = range

40

xrange = range

41

try:

41

try:

42

import re2

42

import re2

43

except ImportError:

43

except ImportError:

44

re2 = None

44

re2 = None

45

46

import testparseutil

46

import testparseutil

47

48

49

def compilere(pat, multiline=False):

49

def compilere(pat, multiline=False):

50

if multiline:

50

if multiline:

51

pat = '(?m)' + pat

51

pat = '(?m)' + pat

52

if re2:

52

if re2:

53

try:

53

try:

54

return re2.compile(pat)

54

return re2.compile(pat)

55

except re2.error:

55

except re2.error:

56

pass

56

pass

57

return re.compile(pat)

57

return re.compile(pat)

58

59

60

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

60

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

61

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

61

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

62

_repquotefixedmap = {

62

_repquotefixedmap = {

63

' ': ' ',

63

' ': ' ',

64

'\n': '\n',

64

'\n': '\n',

65

'.': 'p',

65

'.': 'p',

66

':': 'q',

66

':': 'q',

67

'%': '%',

67

'%': '%',

68

'\\': 'b',

68

'\\': 'b',

69

'*': 'A',

69

'*': 'A',

70

'+': 'P',

70

'+': 'P',

71

'-': 'M',

71

'-': 'M',

72

}

72

}

73

74

75

def _repquoteencodechr(i):

75

def _repquoteencodechr(i):

76

if i > 255:

76

if i > 255:

77

return 'u'

77

return 'u'

78

c = chr(i)

78

c = chr(i)

79

if c in _repquotefixedmap:

79

if c in _repquotefixedmap:

80

return _repquotefixedmap[c]

80

return _repquotefixedmap[c]

81

if c.isalpha():

81

if c.isalpha():

82

return 'x'

82

return 'x'

83

if c.isdigit():

83

if c.isdigit():

84

return 'n'

84

return 'n'

85

return 'o'

85

return 'o'

86

87

88

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

88

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

89

90

91

def repquote(m):

91

def repquote(m):

92

t = m.group('text')

92

t = m.group('text')

93

t = t.translate(_repquotett)

93

t = t.translate(_repquotett)

94

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

94

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

95

96

97

def reppython(m):

97

def reppython(m):

98

comment = m.group('comment')

98

comment = m.group('comment')

99

if comment:

99

if comment:

100

l = len(comment.rstrip())

100

l = len(comment.rstrip())

101

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

101

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

102

return repquote(m)

102

return repquote(m)

103

104

105

def repcomment(m):

105

def repcomment(m):

106

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

106

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

107

108

109

def repccomment(m):

109

def repccomment(m):

110

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

110

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

111

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

111

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

112

113

114

def repcallspaces(m):

114

def repcallspaces(m):

115

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

115

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

116

return m.group(1) + t

116

return m.group(1) + t

117

118

119

def repinclude(m):

119

def repinclude(m):

120

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

120

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

121

122

123

def rephere(m):

123

def rephere(m):

124

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

124

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

125

return m.group(1) + t

125

return m.group(1) + t

126

127

128

testpats = [

128

testpats = [

129

[

129

[

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

(

145

(

146

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

146

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

147

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

147

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

148

),

148

),

149

(r'(^|\|\s*)egrep', "use grep -E for extended grep syntax"),

149

(r'(^|\|\s*)egrep', "use grep -E for extended grep syntax"),

150

(r'(^|\|\s*)fgrep', "use grep -F for fixed string grepping"),

150

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

151

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

151

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

152

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

152

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

153

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

153

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

154

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

154

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

155

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

155

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

156

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

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

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

160

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

161

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

161

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

162

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

162

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

163

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

163

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

164

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

164

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

165

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

165

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

166

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

166

(

167

(

167

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

168

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

168

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

169

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

169

),

170

),

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

(

178

(

178

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

179

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

179

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

180

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

180

),

181

),

181

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

182

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

182

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

183

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

183

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

184

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

184

(

185

(

185

r'find.*-printf',

186

r'find.*-printf',

186

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

187

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

187

),

188

),

188

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

189

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

189

],

190

],

190

# warnings

191

# warnings

191

[

192

[

192

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

193

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

193

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

194

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

194

(r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`", "no-pwd-check"),

195

(r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`", "no-pwd-check"),

195

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

196

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

196

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

197

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

197

],

198

],

198

]

199

]

199

200

testfilters = [

201

testfilters = [

201

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

202

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

202

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

203

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

203

]

204

]

204

205

uprefix = r"^ \$ "

206

uprefix = r"^ \$ "

206

utestpats = [

207

utestpats = [

207

[

208

[

208

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

209

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

209

(

210

(

210

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

211

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

211

"use regex test output patterns instead of sed",

212

"use regex test output patterns instead of sed",

212

),

213

),

213

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

214

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

214

(

215

(

215

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

216

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

216

"explicit exit code checks unnecessary",

217

"explicit exit code checks unnecessary",

217

),

218

),

218

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

219

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

219

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

220

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

220

(

221

(

221

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

222

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

222

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

223

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

223

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

224

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

224

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

225

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

225

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

226

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

226

(

227

(

227

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

228

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

228

'use $LOCALIP not an explicit loopback address',

229

'use $LOCALIP not an explicit loopback address',

229

),

230

),

230

(

231

(

231

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

232

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

232

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

233

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

233

),

234

),

234

(

235

(

235

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

236

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

236

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

237

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

237

),

238

),

238

(

239

(

239

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

240

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

240

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

241

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

241

),

242

),

242

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

243

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

243

(

244

(

244

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

245

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

245

"glob timezone field in diff output for portability",

246

"glob timezone field in diff output for portability",

246

),

247

),

247

(

248

(

248

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

249

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

249

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

250

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

250

),

251

),

251

(

252

(

252

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

253

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

253

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

254

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

254

),

255

),

255

(

256

(

256

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

257

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

257

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

258

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

258

),

259

),

259

(

260

(

260

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

261

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

261

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

262

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

262

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

263

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

263

),

264

),

264

],

265

],

265

# warnings

266

# warnings

266

[

267

[

267

(

268

(

268

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

269

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

269

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

270

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

270

),

271

),

271

],

272

],

272

]

273

]

273

274

# transform plain test rules to unified test's

275

# transform plain test rules to unified test's

275

for i in [0, 1]:

276

for i in [0, 1]:

276

for tp in testpats[i]:

277

for tp in testpats[i]:

277

p = tp[0]

278

p = tp[0]

278

m = tp[1]

279

m = tp[1]

279

if p.startswith('^'):

280

if p.startswith('^'):

280

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

281

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

281

else:

282

else:

282

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

283

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

283

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

284

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

284

285

# don't transform the following rules:

286

# don't transform the following rules:

286

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

287

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

287

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

288

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

288

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

289

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

289

290

utestfilters = [

291

utestfilters = [

291

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

292

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

292

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

293

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

293

]

294

]

294

295

# common patterns to check *.py

296

# common patterns to check *.py

296

commonpypats = [

297

commonpypats = [

297

[

298

[

298

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

299

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

299

(

300

(

300

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

301

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

301

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

302

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

302

),

303

),

303

(

304

(

304

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

305

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

305

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

306

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

306

),

307

),

307

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

308

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

308

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

309

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

309

(

310

(

310

r'\bdict\(.*=',

311

r'\bdict\(.*=',

311

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

312

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

312

'dict-from-generator',

313

'dict-from-generator',

313

),

314

),

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

(

324

(

324

(

325

(

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

# more lines at the same indent level

330

# more lines at the same indent level

330

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

331

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

331

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

332

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

332

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

333

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

333

),

334

),

334

'omit superfluous pass',

335

'omit superfluous pass',

335

),

336

),

336

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

337

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

337

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

338

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

338

(

339

(

339

340

340

"linebreak after :",

341

"linebreak after :",

341

),

342

),

342

(

343

(

343

r'\b(%s)\('

344

r'\b(%s)\('

344

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

345

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

345

"Python keyword is not a function",

346

"Python keyword is not a function",

346

),

347

),

347

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

348

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

348

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

349

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

349

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

350

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

350

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

351

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

351

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

352

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

352

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

353

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

353

(

354

(

354

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

355

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

355

"gratuitous whitespace in () or []",

356

"gratuitous whitespace in () or []",

356

),

357

),

357

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

358

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

358

(

359

(

359

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

360

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

360

"missing whitespace around operator",

361

"missing whitespace around operator",

361

),

362

),

362

(

363

(

363

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

364

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

364

"missing whitespace around operator",

365

"missing whitespace around operator",

365

),

366

),

366

(

367

(

367

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

368

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

368

"missing whitespace around operator",

369

"missing whitespace around operator",

369

),

370

),

370

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

371

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

371

(

372

(

372

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

373

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

373

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

374

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

374

),

375

),

375

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

376

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

376

(

377

(

377

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

378

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

378

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

379

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

379

),

380

),

380

(

381

(

381

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

382

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

382

"use True/False for constant Boolean expression",

383

"use True/False for constant Boolean expression",

383

),

384

),

384

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

385

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

385

(

386

(

386

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

387

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

387

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

388

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

388

'instead',

389

'instead',

389

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

390

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

390

),

391

),

391

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

392

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

392

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

393

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

393

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

394

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

394

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

395

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

395

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

396

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

396

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

397

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

397

(

398

(

398

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

399

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

399

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

400

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

400

),

401

),

401

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

402

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

402

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

403

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

403

(

404

(

404

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

405

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

405

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

406

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

406

),

407

),

407

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

408

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

408

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

409

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

409

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

410

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

410

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

411

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

411

(

412

(

412

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

413

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

413

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

414

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

414

),

415

),

415

(

416

(

416

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

417

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

417

"use mercurial.policy.importmod instead",

418

"use mercurial.policy.importmod instead",

418

),

419

),

419

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

420

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

420

(

421

(

421

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

422

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

422

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

423

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

423

),

424

),

424

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

425

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

425

],

426

],

426

# warnings

427

# warnings

427

[],

428

[],

428

]

429

]

429

430

# patterns to check normal *.py files

431

# patterns to check normal *.py files

431

pypats = [

432

pypats = [

432

[

433

[

433

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

434

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

434

# consistency of coding rules in Mercurial source tree.

435

# consistency of coding rules in Mercurial source tree.

435

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

436

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

436

# python code fragments embedded in test scripts. Fixing test

437

# python code fragments embedded in test scripts. Fixing test

437

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

438

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

438

# profit than effort.

439

# profit than effort.

439

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

440

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

440

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

441

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

441

(

442

(

442

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

443

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

443

"use util.writefile() instead",

444

"use util.writefile() instead",

444

),

445

),

445

(

446

(

446

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

447

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

447

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

448

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

448

),

449

),

449

(

450

(

450

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

451

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

451

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

452

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

452

),

453

),

453

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

454

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

454

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

455

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

455

# rules depending on implementation of repquote()

456

# rules depending on implementation of repquote()

456

(

457

(

457

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

458

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

458

'string join across lines with no space',

459

'string join across lines with no space',

459

),

460

),

460

(

461

(

461

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

462

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

462

[ \t\n#]*

463

[ \t\n#]*

463

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

464

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

464

# contains translatable message)

465

# contains translatable message)

465

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

466

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

466

(?# sequence consisting of below might precede translatable message

467

(?# sequence consisting of below might precede translatable message

467

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

468

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

468

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

469

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

469

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

470

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

470

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

471

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

471

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

472

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

472

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

473

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

473

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

474

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

474

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

475

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

475

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

476

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

476

),

477

),

477

]

478

]

478

+ commonpypats[0],

479

+ commonpypats[0],

479

# warnings

480

# warnings

480

[

481

[

481

# rules depending on implementation of repquote()

482

# rules depending on implementation of repquote()

482

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

483

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

483

]

484

]

484

+ commonpypats[1],

485

+ commonpypats[1],

485

]

486

]

486

487

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

488

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

488

embeddedpypats = [

489

embeddedpypats = [

489

[] + commonpypats[0],

490

[] + commonpypats[0],

490

# warnings

491

# warnings

491

[] + commonpypats[1],

492

[] + commonpypats[1],

492

]

493

]

493

494

# common filters to convert *.py

495

# common filters to convert *.py

495

commonpyfilters = [

496

commonpyfilters = [

496

(

497

(

497

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

498

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

498

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

499

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

499

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

500

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

500

(?P=quote))""",

501

(?P=quote))""",

501

reppython,

502

reppython,

502

),

503

),

503

]

504

]

504

505

# pattern only for mercurial and extensions

506

# pattern only for mercurial and extensions

506

core_py_pats = [

507

core_py_pats = [

507

[

508

[

508

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

509

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

509

#

510

#

510

# see mercurial.windows.abspath for details

511

# see mercurial.windows.abspath for details

511

(

512

(

512

r'os\.path\.abspath',

513

r'os\.path\.abspath',

513

"use util.abspath instead (windows)",

514

"use util.abspath instead (windows)",

514

r'#.*re-exports',

515

r'#.*re-exports',

515

),

516

),

516

],

517

],

517

# warnings

518

# warnings

518

[],

519

[],

519

]

520

]

520

521

# filters to convert normal *.py files

522

# filters to convert normal *.py files

522

pyfilters = [] + commonpyfilters

523

pyfilters = [] + commonpyfilters

523

524

# non-filter patterns

525

# non-filter patterns

525

pynfpats = [

526

pynfpats = [

526

[

527

[

527

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

528

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

528

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

529

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

529

(

530

(

530

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

531

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

531

"use pycompat.isdarwin",

532

"use pycompat.isdarwin",

532

),

533

),

533

],

534

],

534

# warnings

535

# warnings

535

[],

536

[],

536

]

537

]

537

538

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

539

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

539

embeddedpyfilters = [] + commonpyfilters

540

embeddedpyfilters = [] + commonpyfilters

540

541

# extension non-filter patterns

542

# extension non-filter patterns

542

pyextnfpats = [

543

pyextnfpats = [

543

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

544

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

544

# warnings

545

# warnings

545

[],

546

[],

546

]

547

]

547

548

txtfilters = []

549

txtfilters = []

549

550

txtpats = [

551

txtpats = [

551

[

552

[

552

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

553

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

553

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

554

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

554

],

555

],

555

[],

556

[],

556

]

557

]

557

558

cpats = [

559

cpats = [

559

[

560

[

560

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

561

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

561

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

562

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

562

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

563

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

563

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

564

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

564

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

565

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

565

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

566

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

566

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

567

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

567

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

568

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

568

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

569

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

569

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

570

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

570

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

571

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

571

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

572

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

572

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

573

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

573

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

574

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

574

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

575

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

575

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

576

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

576

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

577

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

577

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

578

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

578

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

579

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

579

# rules depending on implementation of repquote()

580

# rules depending on implementation of repquote()

580

],

581

],

581

# warnings

582

# warnings

582

[

583

[

583

# rules depending on implementation of repquote()

584

# rules depending on implementation of repquote()

584

],

585

],

585

]

586

]

586

587

cfilters = [

588

cfilters = [

588

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

589

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

589

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

590

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

590

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

591

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

591

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

592

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

592

]

593

]

593

594

inutilpats = [

595

inutilpats = [

595

[

596

[

596

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

597

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

597

],

598

],

598

# warnings

599

# warnings

599

[],

600

[],

600

]

601

]

601

602

inrevlogpats = [

603

inrevlogpats = [

603

[

604

[

604

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

605

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

605

],

606

],

606

# warnings

607

# warnings

607

[],

608

[],

608

]

609

]

609

610

webtemplatefilters = []

611

webtemplatefilters = []

611

612

webtemplatepats = [

613

webtemplatepats = [

613

[],

614

[],

614

[

615

[

615

(

616

(

616

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

617

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

617

'follow desc keyword with either firstline or websub',

618

'follow desc keyword with either firstline or websub',

618

),

619

),

619

],

620

],

620

]

621

]

621

622

allfilesfilters = []

623

allfilesfilters = []

623

624

allfilespats = [

625

allfilespats = [

625

[

626

[

626

(

627

(

627

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

628

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

628

'use mercurial-scm.org domain URL',

629

'use mercurial-scm.org domain URL',

629

),

630

),

630

(

631

(

631

r'mercurial@selenic\.com',

632

r'mercurial@selenic\.com',

632

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

633

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

633

),

634

),

634

(

635

(

635

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

636

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

636

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

637

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

637

),

638

),

638

],

639

],

639

# warnings

640

# warnings

640

[],

641

[],

641

]

642

]

642

643

py3pats = [

644

py3pats = [

644

[

645

[

645

(

646

(

646

r'os\.environ',

647

r'os\.environ',

647

"use encoding.environ instead (py3)",

648

"use encoding.environ instead (py3)",

648

r'#.*re-exports',

649

r'#.*re-exports',

649

),

650

),

650

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

651

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

651

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

652

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

652

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

653

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

653

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

654

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

654

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

655

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

655

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

656

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

656

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

657

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

657

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

658

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

658

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

659

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

659

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

660

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

660

],

661

],

661

# warnings

662

# warnings

662

[],

663

[],

663

]

664

]

664

665

checks = [

666

checks = [

666

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

667

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

667

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

668

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

668

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

669

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

669

(

670

(

670

'python 3',

671

'python 3',

671

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

672

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

672

'',

673

'',

673

pyfilters,

674

pyfilters,

674

py3pats,

675

py3pats,

675

),

676

),

676

(

677

(

677

'core files',

678

'core files',

678

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

679

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

679

'',

680

'',

680

pyfilters,

681

pyfilters,

681

core_py_pats,

682

core_py_pats,

682

),

683

),

683

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

684

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

684

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

685

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

685

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

686

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

686

(

687

(

687

'layering violation repo in revlog',

688

'layering violation repo in revlog',

688

r'mercurial/revlog\.py',

689

r'mercurial/revlog\.py',

689

'',

690

'',

690

pyfilters,

691

pyfilters,

691

inrevlogpats,

692

inrevlogpats,

692

),

693

),

693

(

694

(

694

'layering violation ui in util',

695

'layering violation ui in util',

695

r'mercurial/util\.py',

696

r'mercurial/util\.py',

696

'',

697

'',

697

pyfilters,

698

pyfilters,

698

inutilpats,

699

inutilpats,

699

),

700

),

700

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

701

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

701

(

702

(

702

'web template',

703

'web template',

703

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

704

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

704

'',

705

'',

705

webtemplatefilters,

706

webtemplatefilters,

706

webtemplatepats,

707

webtemplatepats,

707

),

708

),

708

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

709

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

709

]

710

]

710

711

# (desc,

712

# (desc,

712

# func to pick up embedded code fragments,

713

# func to pick up embedded code fragments,

713

# list of patterns to convert target files

714

# list of patterns to convert target files

714

# list of patterns to detect errors/warnings)

715

# list of patterns to detect errors/warnings)

715

embeddedchecks = [

716

embeddedchecks = [

716

(

717

(

717

'embedded python',

718

'embedded python',

718

testparseutil.pyembedded,

719

testparseutil.pyembedded,

719

embeddedpyfilters,

720

embeddedpyfilters,

720

embeddedpypats,

721

embeddedpypats,

721

)

722

)

722

]

723

]

723

724

725

def _preparepats():

726

def _preparepats():

726

def preparefailandwarn(failandwarn):

727

def preparefailandwarn(failandwarn):

727

for pats in failandwarn:

728

for pats in failandwarn:

728

for i, pseq in enumerate(pats):

729

for i, pseq in enumerate(pats):

729

# fix-up regexes for multi-line searches

730

# fix-up regexes for multi-line searches

730

p = pseq[0]

731

p = pseq[0]

731

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

732

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

732

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

733

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

733

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

734

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

734

# now we replace other \s instances.

735

# now we replace other \s instances.

735

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

736

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

736

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

737

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

737

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

738

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

738

739

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

740

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

740

741

def preparefilters(filters):

742

def preparefilters(filters):

742

for i, flt in enumerate(filters):

743

for i, flt in enumerate(filters):

743

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

744

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

744

745

for cs in (checks, embeddedchecks):

746

for cs in (checks, embeddedchecks):

746

for c in cs:

747

for c in cs:

747

failandwarn = c[-1]

748

failandwarn = c[-1]

748

preparefailandwarn(failandwarn)

749

preparefailandwarn(failandwarn)

749

750

filters = c[-2]

751

filters = c[-2]

751

preparefilters(filters)

752

preparefilters(filters)

752

753

754

class norepeatlogger:

755

class norepeatlogger:

755

def __init__(self):

756

def __init__(self):

756

self._lastseen = None

757

self._lastseen = None

757

758

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

759

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

759

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

760

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

760

761

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

762

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

762

of multiple errors.

763

of multiple errors.

763

764

:fname: filename

765

:fname: filename

765

:lineno: line number

766

:lineno: line number

766

:line: actual content of the line

767

:line: actual content of the line

767

:msg: error message

768

:msg: error message

768

"""

769

"""

769

msgid = fname, lineno, line

770

msgid = fname, lineno, line

770

if msgid != self._lastseen:

771

if msgid != self._lastseen:

771

if blame:

772

if blame:

772

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

773

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

773

else:

774

else:

774

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

775

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

775

print(" > %s" % line)

776

print(" > %s" % line)

776

self._lastseen = msgid

777

self._lastseen = msgid

777

print(" " + msg)

778

print(" " + msg)

778

779

780

_defaultlogger = norepeatlogger()

781

_defaultlogger = norepeatlogger()

781

782

783

def getblame(f):

784

def getblame(f):

784

lines = []

785

lines = []

785

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

786

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

786

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

787

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

787

user, rev = start.split()

788

user, rev = start.split()

788

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

789

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

789

return lines

790

return lines

790

791

792

def checkfile(

793

def checkfile(

793

f,

794

f,

794

logfunc=_defaultlogger.log,

795

logfunc=_defaultlogger.log,

795

maxerr=None,

796

maxerr=None,

796

warnings=False,

797

warnings=False,

797

blame=False,

798

blame=False,

798

debug=False,

799

debug=False,

799

lineno=True,

800

lineno=True,

800

):

801

):

801

"""checks style and portability of a given file

802

"""checks style and portability of a given file

802

803

:f: filepath

804

:f: filepath

804

:logfunc: function used to report error

805

:logfunc: function used to report error

805

logfunc(filename, linenumber, linecontent, errormessage)

806

logfunc(filename, linenumber, linecontent, errormessage)

806

:maxerr: number of error to display before aborting.

807

:maxerr: number of error to display before aborting.

807

Set to false (default) to report all errors

808

Set to false (default) to report all errors

808

809

return True if no error is found, False otherwise.

810

return True if no error is found, False otherwise.

810

"""

811

"""

811

result = True

812

result = True

812

813

try:

814

try:

814

with opentext(f) as fp:

815

with opentext(f) as fp:

815

try:

816

try:

816

pre = fp.read()

817

pre = fp.read()

817

except UnicodeDecodeError as e:

818

except UnicodeDecodeError as e:

818

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

819

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

819

return result

820

return result

820

except IOError as e:

821

except IOError as e:

821

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

822

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

822

return result

823

return result

823

824

# context information shared while single checkfile() invocation

825

# context information shared while single checkfile() invocation

825

context = {'blamecache': None}

826

context = {'blamecache': None}

826

827

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

828

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

828

if debug:

829

if debug:

829

print(name, f)

830

print(name, f)

830

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

831

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

831

if debug:

832

if debug:

832

print(

833

print(

833

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

834

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

834

)

835

)

835

continue

836

continue

836

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

837

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

837

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

838

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

838

# no- check- code

839

# no- check- code

839

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

840

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

840

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

841

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

841

# spelling, we write it with the expected spelling from

842

# spelling, we write it with the expected spelling from

842

# tests/test-check-code.t

843

# tests/test-check-code.t

843

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

844

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

844

return "Skip" # skip checking this file

845

return "Skip" # skip checking this file

845

846

fc = _checkfiledata(

847

fc = _checkfiledata(

847

name,

848

name,

848

f,

849

f,

849

pre,

850

pre,

850

filters,

851

filters,

851

pats,

852

pats,

852

context,

853

context,

853

logfunc,

854

logfunc,

854

maxerr,

855

maxerr,

855

warnings,

856

warnings,

856

blame,

857

blame,

857

debug,

858

debug,

858

lineno,

859

lineno,

859

)

860

)

860

if fc:

861

if fc:

861

result = False

862

result = False

862

863

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

864

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

864

if debug:

865

if debug:

865

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

866

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

866

867

prelines = pre.splitlines()

868

prelines = pre.splitlines()

868

embeddederros = []

869

embeddederros = []

869

for name, embedded, filters, pats in embeddedchecks:

870

for name, embedded, filters, pats in embeddedchecks:

870

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

871

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

871

# nubmer of errors in an actual file per entry of

872

# nubmer of errors in an actual file per entry of

872

# (embedded)checks"

873

# (embedded)checks"

873

curmaxerr = maxerr

874

curmaxerr = maxerr

874

875

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

876

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

876

filename, starts, ends, code = found

877

filename, starts, ends, code = found

877

fc = _checkfiledata(

878

fc = _checkfiledata(

878

name,

879

name,

879

f,

880

f,

880

code,

881

code,

881

filters,

882

filters,

882

pats,

883

pats,

883

context,

884

context,

884

logfunc,

885

logfunc,

885

curmaxerr,

886

curmaxerr,

886

warnings,

887

warnings,

887

blame,

888

blame,

888

debug,

889

debug,

889

lineno,

890

lineno,

890

offset=starts - 1,

891

offset=starts - 1,

891

)

892

)

892

if fc:

893

if fc:

893

result = False

894

result = False

894

if curmaxerr:

895

if curmaxerr:

895

if fc >= curmaxerr:

896

if fc >= curmaxerr:

896

break

897

break

897

curmaxerr -= fc

898

curmaxerr -= fc

898

899

return result

900

return result

900

901

902

def _checkfiledata(

903

def _checkfiledata(

903

name,

904

name,

904

f,

905

f,

905

filedata,

906

filedata,

906

filters,

907

filters,

907

pats,

908

pats,

908

context,

909

context,

909

logfunc,

910

logfunc,

910

maxerr,

911

maxerr,

911

warnings,

912

warnings,

912

blame,

913

blame,

913

debug,

914

debug,

914

lineno,

915

lineno,

915

offset=None,

916

offset=None,

916

):

917

):

917

"""Execute actual error check for file data

918

"""Execute actual error check for file data

918

919

:name: of the checking category

920

:name: of the checking category

920

:f: filepath

921

:f: filepath

921

:filedata: content of a file

922

:filedata: content of a file

922

:filters: to be applied before checking

923

:filters: to be applied before checking

923

:pats: to detect errors

924

:pats: to detect errors

924

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

925

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

925

Valid keys: 'blamecache'.

926

Valid keys: 'blamecache'.

926

:logfunc: function used to report error

927

:logfunc: function used to report error

927

logfunc(filename, linenumber, linecontent, errormessage)

928

logfunc(filename, linenumber, linecontent, errormessage)

928

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

929

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

929

report all errors

930

report all errors

930

:warnings: whether warning level checks should be applied

931

:warnings: whether warning level checks should be applied

931

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

932

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

932

:debug: whether debug information should be displayed

933

:debug: whether debug information should be displayed

933

:lineno: whether lineno should be displayed at error reporting

934

:lineno: whether lineno should be displayed at error reporting

934

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

935

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

935

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

936

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

936

from offset=None)

937

from offset=None)

937

938

returns number of detected errors.

939

returns number of detected errors.

939

"""

940

"""

940

blamecache = context['blamecache']

941

blamecache = context['blamecache']

941

if offset is None:

942

if offset is None:

942

lineoffset = 0

943

lineoffset = 0

943

else:

944

else:

944

lineoffset = offset

945

lineoffset = offset

945

946

fc = 0

947

fc = 0

947

pre = post = filedata

948

pre = post = filedata

948

949

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

950

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

950

for p, r in filters:

951

for p, r in filters:

951

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

952

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

952

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

953

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

953

if warnings:

954

if warnings:

954

pats = pats[0] + pats[1]

955

pats = pats[0] + pats[1]

955

else:

956

else:

956

pats = pats[0]

957

pats = pats[0]

957

# print post # uncomment to show filtered version

958

# print post # uncomment to show filtered version

958

959

if debug:

960

if debug:

960

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

961

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

961

962

prelines = None

963

prelines = None

963

errors = []

964

errors = []

964

for i, pat in enumerate(pats):

965

for i, pat in enumerate(pats):

965

if len(pat) == 3:

966

if len(pat) == 3:

966

p, msg, ignore = pat

967

p, msg, ignore = pat

967

else:

968

else:

968

p, msg = pat

969

p, msg = pat

969

ignore = None

970

ignore = None

970

if i >= nerrs:

971

if i >= nerrs:

971

msg = "warning: " + msg

972

msg = "warning: " + msg

972

973

pos = 0

974

pos = 0

974

n = 0

975

n = 0

975

for m in p.finditer(post):

976

for m in p.finditer(post):

976

if prelines is None:

977

if prelines is None:

977

prelines = pre.splitlines()

978

prelines = pre.splitlines()

978

postlines = post.splitlines(True)

979

postlines = post.splitlines(True)

979

980

start = m.start()

981

start = m.start()

981

while n < len(postlines):

982

while n < len(postlines):

982

step = len(postlines[n])

983

step = len(postlines[n])

983

if pos + step > start:

984

if pos + step > start:

984

break

985

break

985

pos += step

986

pos += step

986

n += 1

987

n += 1

987

l = prelines[n]

988

l = prelines[n]

988

989

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

990

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

990

if debug:

991

if debug:

991

print(

992

print(

992

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

993

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

993

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

994

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

994

)

995

)

995

continue

996

continue

996

bd = ""

997

bd = ""

997

if blame:

998

if blame:

998

bd = 'working directory'

999

bd = 'working directory'

999

if blamecache is None:

1000

if blamecache is None:

1000

blamecache = getblame(f)

1001

blamecache = getblame(f)

1001

context['blamecache'] = blamecache

1002

context['blamecache'] = blamecache

1002

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

1003

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

1003

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

1004

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

1004

if offset is None and bl == l:

1005

if offset is None and bl == l:

1005

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

1006

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

1006

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

1007

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

1007

# "offset is not None" means "checking

1008

# "offset is not None" means "checking

1008

# embedded code fragment". In this case,

1009

# embedded code fragment". In this case,

1009

# "l" does not have information about the

1010

# "l" does not have information about the

1010

# beginning of an *original* line in the

1011

# beginning of an *original* line in the

1011

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

1012

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

1012

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

1013

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

1013

# show "maybe" for a little loose

1014

# show "maybe" for a little loose

1014

# examination.

1015

# examination.

1015

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

1016

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

1016

1017

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

1018

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

1018

1019

errors.sort()

1020

errors.sort()

1020

for e in errors:

1021

for e in errors:

1021

logfunc(*e)

1022

logfunc(*e)

1022

fc += 1

1023

fc += 1

1023

if maxerr and fc >= maxerr:

1024

if maxerr and fc >= maxerr:

1024

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

1025

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

1025

break

1026

break

1026

1027

return fc

1028

return fc

1028

1029

1030

def main():

1031

def main():

1031

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

1032

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

1032

parser.add_option(

1033

parser.add_option(

1033

"-w",

1034

"-w",

1034

"--warnings",

1035

"--warnings",

1035

action="store_true",

1036

action="store_true",

1036

help="include warning-level checks",

1037

help="include warning-level checks",

1037

)

1038

)

1038

parser.add_option(

1039

parser.add_option(

1039

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

1040

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

1040

)

1041

)

1041

parser.add_option(

1042

parser.add_option(

1042

"-b",

1043

"-b",

1043

"--blame",

1044

"--blame",

1044

action="store_true",

1045

action="store_true",

1045

help="use annotate to generate blame info",

1046

help="use annotate to generate blame info",

1046

)

1047

)

1047

parser.add_option(

1048

parser.add_option(

1048

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

1049

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

1049

)

1050

)

1050

parser.add_option(

1051

parser.add_option(

1051

"",

1052

"",

1052

"--nolineno",

1053

"--nolineno",

1053

action="store_false",

1054

action="store_false",

1054

dest='lineno',

1055

dest='lineno',

1055

help="don't show line numbers",

1056

help="don't show line numbers",

1056

)

1057

)

1057

1058

parser.set_defaults(

1059

parser.set_defaults(

1059

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

1060

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

1060

)

1061

)

1061

(options, args) = parser.parse_args()

1062

(options, args) = parser.parse_args()

1062

1063

if len(args) == 0:

1064

if len(args) == 0:

1064

check = glob.glob("*")

1065

check = glob.glob("*")

1065

elif args == ['-']:

1066

elif args == ['-']:

1066

# read file list from stdin

1067

# read file list from stdin

1067

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

1068

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

1068

else:

1069

else:

1069

check = args

1070

check = args

1070

1071

_preparepats()

1072

_preparepats()

1072

1073

ret = 0

1074

ret = 0

1074

for f in check:

1075

for f in check:

1075

if not checkfile(

1076

if not checkfile(

1076

f,

1077

f,

1077

maxerr=options.per_file,

1078

maxerr=options.per_file,

1078

warnings=options.warnings,

1079

warnings=options.warnings,

1079

blame=options.blame,

1080

blame=options.blame,

1080

debug=options.debug,

1081

debug=options.debug,

1081

lineno=options.lineno,

1082

lineno=options.lineno,

1082

):

1083

):

1083

ret = 1

1084

ret = 1

1084

return ret

1085

return ret

1085

1086

1087

if __name__ == "__main__":

1088

if __name__ == "__main__":

1088

sys.exit(main())

1089

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
             """
             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*)egrep', "use grep -E for extended grep syntax"),
+                    (r'(^|\|\s*)fgrep', "use grep -F for fixed string grepping"),
                     (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`", "no-pwd-check"),
                     (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*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                         "linebreak after :",
                     ),
                     (
                         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'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'^(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:
                 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())

             initialize
               $ make_changes() {
               >     d=`pwd`
               >     [ ! -z $1 ] && cd $1
               >     echo "test `basename \`pwd\``" >> test
               >     hg commit -Am"${2:-test}"
               >     r=$?
               >     cd $d
               >     return $r
               > }
               $ ls -1a
               .
               ..
               $ hg init a
               $ cd a
               $ echo 'test' > test; hg commit -Am'test'
               adding test
             clone to b
               $ mkdir ../b
               $ cd ../b
               $ hg clone ../a .
               updating to branch default
 files updated, 0 files merged, 0 files removed, 0 files unresolved
               $ echo "[extensions]" >> .hg/hgrc
               $ echo "bookflow=" >> .hg/hgrc
               $ hg branch X
               abort: creating named branches is disabled and you should use bookmarks
               (see 'hg help bookflow')
               [255]
               $ hg bookmark X
               $ hg bookmarks
               * X                         0:* (glob)
               $ hg bookmark X
               abort: bookmark X already exists, to move use the --rev option
               [255]
               $ make_changes
               $ hg push ../a -q
               $ hg bookmarks
                \* X                         1:* (glob)
             change a
               $ cd ../a
               $ hg up
 files updated, 0 files merged, 0 files removed, 0 files unresolved
               $ echo 'test' >> test; hg commit -Am'test'
             pull in b
               $ cd ../b
               $ hg pull -u
               pulling from $TESTTMP/a
               searching for changes
               adding changesets
               adding manifests
               adding file changes
               added 1 changesets with 1 changes to 1 files
               new changesets * (glob)
 files updated, 0 files merged, 0 files removed, 0 files unresolved
               (leaving bookmark X)
               $ hg status
               $ hg bookmarks
                  X                         1:* (glob)
             check protection of @ bookmark
               $ hg bookmark @
               $ hg bookmarks
                \* @                         2:* (glob)
                  X                         1:* (glob)
               $ make_changes
               abort: cannot commit, bookmark @ is protected
               [255]
               $ hg status
               M test
               $ hg bookmarks
                \* @                         2:* (glob)
                  X                         1:* (glob)
               $ hg --config bookflow.protect= commit  -Am"Updated test"
               $ hg bookmarks
                \* @                         3:* (glob)
                  X                         1:* (glob)
             check requirement for an active bookmark
               $ hg bookmark -i
               $ hg bookmarks
                  @                         3:* (glob)
                  X                         1:* (glob)
               $ make_changes
               abort: cannot commit without an active bookmark
               [255]
               $ hg revert test
               $ rm test.orig
               $ hg status
             make the bookmark move by updating it on a, and then pulling
             # add a commit to a
               $ cd ../a
               $ hg bookmark X
               $ hg bookmarks
                \* X                         2:* (glob)
               $ make_changes
               $ hg bookmarks
                * X                         3:81af7977fdb9
             # go back to b, and check out X
               $ cd ../b
               $ hg up X
 files updated, 0 files merged, 0 files removed, 0 files unresolved
               (activating bookmark X)
               $ hg bookmarks
                  @                         3:* (glob)
                \* X                         1:* (glob)
             # pull, this should move the bookmark forward, because it was changed remotely
               $ hg pull -u | grep "updating to active bookmark X"
               updating to active bookmark X
               $ hg bookmarks
                  @                         3:* (glob)
                * X                         4:81af7977fdb9
             the bookmark should not move if it diverged from remote
               $ hg -R ../a status
               $ hg -R ../b status
               $ make_changes ../a
               $ make_changes ../b
               $ hg -R ../a status
               $ hg -R ../b status
               $ hg -R ../a bookmarks
                * X                         4:238292f60a57
               $ hg -R ../b bookmarks
                  @                         3:* (glob)
                * X                         5:096f7e86892d
               $ cd ../b
               $ # make sure we cannot push after bookmarks diverged
               $ hg push -B X | grep abort
               abort: push creates new remote head * with bookmark 'X' (glob)
               (pull and merge or see 'hg help push' for details about pushing new heads)
               [1]
               $ hg pull -u | grep divergent
               divergent bookmark X stored as X@default
 other divergent bookmarks for "X"
               $ hg bookmarks
                  @                         3:* (glob)
                * X                         5:096f7e86892d
                  X@default                 6:238292f60a57
               $ hg id -in
 f7e86892d 5
               $ make_changes
               $ hg status
               $ hg bookmarks
                  @                         3:* (glob)
                * X                         7:227f941aeb07
                  X@default                 6:238292f60a57
             now merge with the remote bookmark
               $ hg merge X@default --tool :local -q
               $ hg status
               M test
               $ hg commit -m"Merged with X@default"
               $ hg bookmarks
                  @                         3:* (glob)
                * X                         8:26fed9bb3219
               $ hg push -B X | grep bookmark
               pushing to $TESTTMP/a (?)
               updating bookmark X
               $ cd ../a
               $ hg up -q
               $ hg bookmarks
                * X                         7:26fed9bb3219
             test hg pull when there is more than one descendant
               $ cd ../a
               $ hg bookmark Z
               $ hg bookmark Y
               $ make_changes . YY
               $ hg up Z -q
               $ make_changes . ZZ
               created new head
               $ hg bookmarks
                  X                         7:26fed9bb3219
                  Y                         8:131e663dbd2a
                * Z                         9:b74a4149df25
               $ hg log -r 'p1(Y)' -r 'p1(Z)' -T '{rev}\n' # prove that Y and Z share the same parent
               $ hg log -r 'Y%Z' -T '{rev}\n'  # revs in Y but not in Z
               $ hg log -r 'Z%Y' -T '{rev}\n'  # revs in Z but not in Y
               $ cd ../b
               $ hg pull -uq
               $ hg id
               b74a4149df25 tip Z
               $ hg bookmarks | grep \*  # no active bookmark
               [1]
             test shelving
               $ cd ../a
               $ echo anotherfile > anotherfile # this change should not conflict
               $ hg add anotherfile
               $ hg commit -m"Change in a"
               $ cd ../b
               $ hg up Z | grep Z
               (activating bookmark Z)
               $ hg book | grep \* # make sure active bookmark
                \* Z                         10:* (glob)
               $ echo "test b" >> test
               $ hg diff --stat
                test |  1 +
 files changed, 1 insertions(+), 0 deletions(-)
               $ hg shelve
               shelved as Z
 files updated, 0 files merged, 0 files removed, 0 files unresolved
               $ hg pull -uq
               $ hg unshelve
               unshelving change 'Z'
               rebasing shelved changes
               $ hg diff --stat
                test |  1 +
 files changed, 1 insertions(+), 0 deletions(-)
             make the bookmark move by updating it on a, and then pulling with a local change
             # add a commit to a
               $ cd ../a
-              $ hg up -C X |fgrep  "activating bookmark X"
+              $ hg up -C X |grep -F  "activating bookmark X"
               (activating bookmark X)
             # go back to b, and check out X
               $ cd ../b
-              $ hg up -C X |fgrep  "activating bookmark X"
+              $ hg up -C X |grep -F  "activating bookmark X"
               (activating bookmark X)
             # update and push from a
               $ make_changes ../a
               created new head
               $ echo "more" >> test
-              $ hg pull -u 2>&1 | fgrep -v TESTTMP| fgrep -v "searching for changes" | fgrep -v adding
+              $ hg pull -u 2>&1 | grep -F -v TESTTMP| grep -F -v "searching for changes" | grep -F -v adding
               pulling from $TESTTMP/a
               updating bookmark X
               added 1 changesets with 0 changes to 0 files (+1 heads)
               new changesets * (glob)
               updating to active bookmark X
               merging test
               warning: conflicts while merging test! (edit, then use 'hg resolve --mark')
 files updated, 0 files merged, 0 files removed, 1 files unresolved
               use 'hg resolve' to retry unresolved file merges
               $ hg update -Cq
               $ rm test.orig
             make sure that commits aren't possible if working directory is not pointing to active bookmark
               $ hg -R ../a status
               $ hg -R ../b status
               $ hg -R ../a id -i
 a6e592ec06
               $ hg -R ../a book | grep X
                \* X                         \d+:36a6e592ec06 (re)
               $ hg -R ../b id -i
 a6e592ec06
               $ hg -R ../b book | grep X
                \* X                         \d+:36a6e592ec06 (re)
               $ make_changes ../a
               $ hg -R ../a book | grep X
                \* X                         \d+:f73a71c992b8 (re)
               $ cd ../b
               $ hg pull  2>&1 | grep -v add | grep -v pulling | grep -v searching | grep -v changeset
               updating bookmark X
               (run 'hg update' to get a working copy)
               working directory out of sync with active bookmark, run 'hg up X'
               $ hg id -i # we're still on the old commit
 a6e592ec06
               $ hg book | grep X # while the bookmark moved
                \* X                         \d+:f73a71c992b8 (re)
               $ make_changes
               abort: cannot commit, working directory out of sync with active bookmark
               (run 'hg up X')
               [255]
               $ hg up -Cq -r .  # cleanup local changes
               $ hg status
               $ hg id -i # we're still on the old commit
 a6e592ec06
               $ hg up X -q
               $ hg id -i # now we're on X
               f73a71c992b8
               $ hg book | grep X
                \* X                         \d+:f73a71c992b8 (re)