upstream/mercurial-mirror Commit - r29517:f1fdd7e7

1

#!/usr/bin/env python

1

#!/usr/bin/env python

2

#

2

#

3

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

3

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

4

#

4

#

5

6

#

6

#

7

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

7

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

8

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

8

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

9

10

"""style and portability checker for Mercurial

10

"""style and portability checker for Mercurial

11

12

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

12

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

13

* do the work-around the rule suggests

13

* do the work-around the rule suggests

14

* doublecheck that it is a false match

14

* doublecheck that it is a false match

15

* improve the rule pattern

15

* improve the rule pattern

16

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

16

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

17

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

17

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

18

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

18

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

19

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

19

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

20

"""

20

"""

21

22

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

def opentext(f):

32

def opentext(f):

33

return open(f, encoding='ascii')

33

return open(f, encoding='ascii')

34

try:

34

try:

35

xrange

35

xrange

36

except NameError:

36

except NameError:

37

xrange = range

37

xrange = range

38

try:

38

try:

39

import re2

39

import re2

40

except ImportError:

40

except ImportError:

41

re2 = None

41

re2 = None

42

43

def compilere(pat, multiline=False):

43

def compilere(pat, multiline=False):

44

if multiline:

44

if multiline:

45

pat = '(?m)' + pat

45

pat = '(?m)' + pat

46

if re2:

46

if re2:

47

try:

47

try:

48

return re2.compile(pat)

48

return re2.compile(pat)

49

except re2.error:

49

except re2.error:

50

pass

50

pass

51

return re.compile(pat)

51

return re.compile(pat)

52

53

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

53

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

54

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

54

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

55

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

55

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

56

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

56

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

57

def _repquoteencodechr(i):

57

def _repquoteencodechr(i):

58

if i > 255:

58

if i > 255:

59

return 'u'

59

return 'u'

60

c = chr(i)

60

c = chr(i)

61

if c in _repquotefixedmap:

61

if c in _repquotefixedmap:

62

return _repquotefixedmap[c]

62

return _repquotefixedmap[c]

63

if c.isalpha():

63

if c.isalpha():

64

return 'x'

64

return 'x'

65

if c.isdigit():

65

if c.isdigit():

66

return 'n'

66

return 'n'

67

return 'o'

67

return 'o'

68

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

68

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

69

70

def repquote(m):

70

def repquote(m):

71

t = m.group('text')

71

t = m.group('text')

72

t = t.translate(_repquotett)

72

t = t.translate(_repquotett)

73

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

73

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

74

75

def reppython(m):

75

def reppython(m):

76

comment = m.group('comment')

76

comment = m.group('comment')

77

if comment:

77

if comment:

78

l = len(comment.rstrip())

78

l = len(comment.rstrip())

79

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

79

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

80

return repquote(m)

80

return repquote(m)

81

82

def repcomment(m):

82

def repcomment(m):

83

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

83

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

84

85

def repccomment(m):

85

def repccomment(m):

86

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

86

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

87

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

87

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

88

89

def repcallspaces(m):

89

def repcallspaces(m):

90

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

90

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

91

return m.group(1) + t

91

return m.group(1) + t

92

93

def repinclude(m):

93

def repinclude(m):

94

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

94

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

95

96

def rephere(m):

96

def rephere(m):

97

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

97

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

98

return m.group(1) + t

98

return m.group(1) + t

99

100

101

testpats = [

101

testpats = [

102

[

102

[

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

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

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

"use egrep for extended grep syntax"),

120

"use egrep for extended grep syntax"),

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

],

146

],

147

# warnings

147

# warnings

148

[

148

[

149

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

149

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

150

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

150

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

151

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

151

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

152

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

152

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

153

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

153

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

154

]

154

]

155

]

155

]

156

157

testfilters = [

157

testfilters = [

158

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

158

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

159

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

159

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

160

]

160

]

161

162

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

162

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

163

uprefix = r"^ \$ "

163

uprefix = r"^ \$ "

164

utestpats = [

164

utestpats = [

165

[

165

[

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

"explicit exit code checks unnecessary"),

172

"explicit exit code checks unnecessary"),

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

winglobmsg),

180

winglobmsg),

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

],

207

],

208

# warnings

208

# warnings

209

[

209

[

210

(r'^ [^*?/\n]* $glob$$',

210

(r'^ [^*?/\n]* $glob$$',

211

"glob match with no glob character (?*/)"),

211

"glob match with no glob character (?*/)"),

212

]

212

]

213

]

213

]

214

215

for i in [0, 1]:

215

for i in [0, 1]:

216

for tp in testpats[i]:

216

for tp in testpats[i]:

217

p = tp[0]

217

p = tp[0]

218

m = tp[1]

218

m = tp[1]

219

if p.startswith(r'^'):

219

if p.startswith(r'^'):

220

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

220

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

221

else:

221

else:

222

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

222

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

223

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

223

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

224

225

utestfilters = [

225

utestfilters = [

226

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

226

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

227

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

227

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

228

]

228

]

229

230

pypats = [

230

pypats = [

231

[

231

[

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

'dict-from-generator'),

239

'dict-from-generator'),

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

"don't use camelcase in identifiers"),

256

"don't use camelcase in identifiers"),

257

257

258

"linebreak after :"),

258

"linebreak after :"),

259

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

259

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

260

r'#.*old-style'),

260

r'#.*old-style'),

261

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

261

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

262

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

262

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

263

r'#.*old-style'),

263

r'#.*old-style'),

264

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

264

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

265

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

265

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

266

"Python keyword is not a function"),

266

"Python keyword is not a function"),

267

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

267

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

268

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

268

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

269

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

269

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

270

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

270

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

271

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

271

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

272

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

272

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

273

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

273

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

274

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

274

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

275

"gratuitous whitespace after Python keyword"),

275

"gratuitous whitespace after Python keyword"),

276

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

276

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

277

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

277

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

278

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

278

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

279

"missing whitespace around operator"),

279

"missing whitespace around operator"),

280

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

280

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

281

"missing whitespace around operator"),

281

"missing whitespace around operator"),

282

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

282

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

283

"missing whitespace around operator"),

283

"missing whitespace around operator"),

284

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

284

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

285

"wrong whitespace around ="),

285

"wrong whitespace around ="),

286

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

286

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

287

"no whitespace around = for named parameters"),

287

"no whitespace around = for named parameters"),

288

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

288

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

289

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

289

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

290

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

290

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

291

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

291

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

292

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

292

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

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

"use opener.read() instead"),

299

"use opener.read() instead"),

300

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

300

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

301

"use opener.write() instead"),

301

"use opener.write() instead"),

302

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

302

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

303

"use util.readfile() instead"),

303

"use util.readfile() instead"),

304

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

304

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

305

"use util.writefile() instead"),

305

"use util.writefile() instead"),

306

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

306

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

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

(r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),

318

(r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

336

# rules depending on implementation of repquote()

336

# rules depending on implementation of repquote()

337

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

337

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

338

'string join across lines with no space'),

338

'string join across lines with no space'),

339

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

339

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

340

[ \t\n#]*

340

[ \t\n#]*

341

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

341

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

342

# contains translatable message)

342

# contains translatable message)

343

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

343

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

344

(?# sequence consisting of below might precede translatable message

344

(?# sequence consisting of below might precede translatable message

345

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

345

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

346

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

346

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

347

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

347

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

348

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

348

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

349

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

349

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

350

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

350

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

351

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

351

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

352

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

352

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

353

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

353

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

354

],

354

],

355

# warnings

355

# warnings

356

[

356

[

357

# rules depending on implementation of repquote()

357

# rules depending on implementation of repquote()

358

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

358

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

359

]

359

]

360

]

360

]

361

362

pyfilters = [

362

pyfilters = [

363

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

363

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

364

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

364

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

365

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

365

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

366

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

366

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

367

]

367

]

368

369

txtfilters = []

369

txtfilters = []

370

371

txtpats = [

371

txtpats = [

372

[

372

[

373

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

373

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

374

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

374

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

375

],

375

],

376

[]

376

[]

377

]

377

]

378

379

cpats = [

379

cpats = [

380

[

380

[

381

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

381

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

382

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

382

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

383

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

383

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

384

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

384

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

385

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

385

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

386

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

386

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

387

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

387

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

388

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

388

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

389

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

389

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

390

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

390

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

391

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

391

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

392

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

392

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

393

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

393

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

394

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

394

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

395

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

395

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

396

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

396

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

397

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

397

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

398

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

398

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

399

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

399

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

400

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

400

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

401

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

401

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

402

403

# rules depending on implementation of repquote()

403

# rules depending on implementation of repquote()

404

],

404

],

405

# warnings

405

# warnings

406

[

406

[

407

# rules depending on implementation of repquote()

407

# rules depending on implementation of repquote()

408

]

408

]

409

]

409

]

410

411

cfilters = [

411

cfilters = [

412

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

412

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

413

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

413

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

414

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

414

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

415

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

415

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

416

]

416

]

417

418

inutilpats = [

418

inutilpats = [

419

[

419

[

420

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

420

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

421

],

421

],

422

# warnings

422

# warnings

423

[]

423

[]

424

]

424

]

425

426

inrevlogpats = [

426

inrevlogpats = [

427

[

427

[

428

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

428

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

429

],

429

],

430

# warnings

430

# warnings

431

[]

431

[]

432

]

432

]

433

434

webtemplatefilters = []

434

webtemplatefilters = []

435

436

webtemplatepats = [

436

webtemplatepats = [

437

[],

437

[],

438

[

438

[

439

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

439

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

440

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

440

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

441

]

441

]

442

]

442

]

443

444

checks = [

444

checks = [

445

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

445

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

446

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

446

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

447

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

447

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

448

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

448

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

449

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

449

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

450

pyfilters, inrevlogpats),

450

pyfilters, inrevlogpats),

451

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

451

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

452

inutilpats),

452

inutilpats),

453

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

453

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

454

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

454

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

455

webtemplatefilters, webtemplatepats),

455

webtemplatefilters, webtemplatepats),

456

]

456

]

457

458

def _preparepats():

458

def _preparepats():

459

for c in checks:

459

for c in checks:

460

failandwarn = c[-1]

460

failandwarn = c[-1]

461

for pats in failandwarn:

461

for pats in failandwarn:

462

for i, pseq in enumerate(pats):

462

for i, pseq in enumerate(pats):

463

# fix-up regexes for multi-line searches

463

# fix-up regexes for multi-line searches

464

p = pseq[0]

464

p = pseq[0]

465

# \s doesn't match \n

465

# \s doesn't match \n

466

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

466

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

467

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

467

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

468

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

468

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

469

470

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

470

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

471

filters = c[3]

471

filters = c[3]

472

for i, flt in enumerate(filters):

472

for i, flt in enumerate(filters):

473

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

473

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

474

_preparepats()

474

_preparepats()

475

476

class norepeatlogger(object):

476

class norepeatlogger(object):

477

def __init__(self):

477

def __init__(self):

478

self._lastseen = None

478

self._lastseen = None

479

480

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

480

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

481

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

481

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

482

483

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

483

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

484

of multiple errors.

484

of multiple errors.

485

486

:fname: filename

486

:fname: filename

487

:lineno: line number

487

:lineno: line number

488

:line: actual content of the line

488

:line: actual content of the line

489

:msg: error message

489

:msg: error message

490

"""

490

"""

491

msgid = fname, lineno, line

491

msgid = fname, lineno, line

492

if msgid != self._lastseen:

492

if msgid != self._lastseen:

493

if blame:

493

if blame:

494

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

494

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

495

else:

495

else:

496

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

496

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

497

print(" > %s" % line)

497

print(" > %s" % line)

498

self._lastseen = msgid

498

self._lastseen = msgid

499

print(" " + msg)

499

print(" " + msg)

500

501

_defaultlogger = norepeatlogger()

501

_defaultlogger = norepeatlogger()

502

503

def getblame(f):

503

def getblame(f):

504

lines = []

504

lines = []

505

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

505

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

506

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

506

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

507

user, rev = start.split()

507

user, rev = start.split()

508

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

508

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

509

return lines

509

return lines

510

511

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

511

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

512

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

512

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

513

"""checks style and portability of a given file

513

"""checks style and portability of a given file

514

515

:f: filepath

515

:f: filepath

516

:logfunc: function used to report error

516

:logfunc: function used to report error

517

logfunc(filename, linenumber, linecontent, errormessage)

517

logfunc(filename, linenumber, linecontent, errormessage)

518

:maxerr: number of error to display before aborting.

518

:maxerr: number of error to display before aborting.

519

Set to false (default) to report all errors

519

Set to false (default) to report all errors

520

521

return True if no error is found, False otherwise.

521

return True if no error is found, False otherwise.

522

"""

522

"""

523

blamecache = None

523

blamecache = None

524

result = True

524

result = True

525

526

try:

526

try:

527

with opentext(f) as fp:

527

with opentext(f) as fp:

528

try:

528

try:

529

pre = post = fp.read()

529

pre = post = fp.read()

530

except UnicodeDecodeError as e:

530

except UnicodeDecodeError as e:

531

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

531

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

532

return result

532

return result

533

except IOError as e:

533

except IOError as e:

534

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

534

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

535

return result

535

return result

536

537

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

537

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

538

if debug:

538

if debug:

539

print(name, f)

539

print(name, f)

540

fc = 0

540

fc = 0

541

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

541

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

542

if debug:

542

if debug:

543

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

543

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

544

name, match, f))

544

name, match, f))

545

continue

545

continue

546

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

546

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

547

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

547

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

548

# no- check- code

548

# no- check- code

549

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

549

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

550

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

550

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

551

# spelling, we write it with the expected spelling from

551

# spelling, we write it with the expected spelling from

552

# tests/test-check-code.t

552

# tests/test-check-code.t

553

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

553

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

554

return "Skip" # skip checking this file

554

return "Skip" # skip checking this file

555

for p, r in filters:

555

for p, r in filters:

556

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

556

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

557

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

557

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

558

if warnings:

558

if warnings:

559

pats = pats[0] + pats[1]

559

pats = pats[0] + pats[1]

560

else:

560

else:

561

pats = pats[0]

561

pats = pats[0]

562

# print post # uncomment to show filtered version

562

# print post # uncomment to show filtered version

563

564

if debug:

564

if debug:

565

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

565

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

566

567

prelines = None

567

prelines = None

568

errors = []

568

errors = []

569

for i, pat in enumerate(pats):

569

for i, pat in enumerate(pats):

570

if len(pat) == 3:

570

if len(pat) == 3:

571

p, msg, ignore = pat

571

p, msg, ignore = pat

572

else:

572

else:

573

p, msg = pat

573

p, msg = pat

574

ignore = None

574

ignore = None

575

if i >= nerrs:

575

if i >= nerrs:

576

msg = "warning: " + msg

576

msg = "warning: " + msg

577

578

pos = 0

578

pos = 0

579

n = 0

579

n = 0

580

for m in p.finditer(post):

580

for m in p.finditer(post):

581

if prelines is None:

581

if prelines is None:

582

prelines = pre.splitlines()

582

prelines = pre.splitlines()

583

postlines = post.splitlines(True)

583

postlines = post.splitlines(True)

584

585

start = m.start()

585

start = m.start()

586

while n < len(postlines):

586

while n < len(postlines):

587

step = len(postlines[n])

587

step = len(postlines[n])

588

if pos + step > start:

588

if pos + step > start:

589

break

589

break

590

pos += step

590

pos += step

591

n += 1

591

n += 1

592

l = prelines[n]

592

l = prelines[n]

593

594

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

594

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

595

if debug:

595

if debug:

596

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

596

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

597

name, f, n))

597

name, f, n))

598

continue

598

continue

599

bd = ""

599

bd = ""

600

if blame:

600

if blame:

601

bd = 'working directory'

601

bd = 'working directory'

602

if not blamecache:

602

if not blamecache:

603

blamecache = getblame(f)

603

blamecache = getblame(f)

604

if n < len(blamecache):

604

if n < len(blamecache):

605

bl, bu, br = blamecache[n]

605

bl, bu, br = blamecache[n]

606

if bl == l:

606

if bl == l:

607

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

607

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

608

609

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

609

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

610

result = False

610

result = False

611

612

errors.sort()

612

errors.sort()

613

for e in errors:

613

for e in errors:

614

logfunc(*e)

614

logfunc(*e)

615

fc += 1

615

fc += 1

616

if maxerr and fc >= maxerr:

616

if maxerr and fc >= maxerr:

617

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

617

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

618

break

618

break

619

620

return result

620

return result

621

622

if __name__ == "__main__":

622

if __name__ == "__main__":

623

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

623

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

624

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

624

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

625

help="include warning-level checks")

625

help="include warning-level checks")

626

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

626

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

627

help="max warnings per file")

627

help="max warnings per file")

628

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

628

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

629

help="use annotate to generate blame info")

629

help="use annotate to generate blame info")

630

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

630

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

631

help="show debug information")

631

help="show debug information")

632

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

632

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

633

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

633

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

634

635

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

635

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

636

lineno=True)

636

lineno=True)

637

(options, args) = parser.parse_args()

637

(options, args) = parser.parse_args()

638

639

if len(args) == 0:

639

if len(args) == 0:

640

check = glob.glob("*")

640

check = glob.glob("*")

641

else:

641

else:

642

check = args

642

check = args

643

644

ret = 0

644

ret = 0

645

for f in check:

645

for f in check:

646

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

646

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

647

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

647

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

648

lineno=options.lineno):

648

lineno=options.lineno):

649

ret = 1

649

ret = 1

650

sys.exit(ret)

650

sys.exit(ret)

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

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

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