upstream/mercurial-mirror Commit - r28219:97fe8880

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, # no-py24)

17

(you can append a short comment and match this, like: #re-raises, # no-py24)

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 re, glob, os, sys

22

import re, glob, os, sys

23

import keyword

23

import keyword

24

import optparse

24

import optparse

25

try:

25

try:

26

import re2

26

import re2

27

except ImportError:

27

except ImportError:

28

re2 = None

28

re2 = None

29

30

def compilere(pat, multiline=False):

30

def compilere(pat, multiline=False):

31

if multiline:

31

if multiline:

32

pat = '(?m)' + pat

32

pat = '(?m)' + pat

33

if re2:

33

if re2:

34

try:

34

try:

35

return re2.compile(pat)

35

return re2.compile(pat)

36

except re2.error:

36

except re2.error:

37

pass

37

pass

38

return re.compile(pat)

38

return re.compile(pat)

39

40

def repquote(m):

40

def repquote(m):

41

fromc = '.:'

41

fromc = '.:'

42

tochr = 'pq'

42

tochr = 'pq'

43

def encodechr(i):

43

def encodechr(i):

44

if i > 255:

44

if i > 255:

45

return 'u'

45

return 'u'

46

c = chr(i)

46

c = chr(i)

47

if c in ' \n':

47

if c in ' \n':

48

return c

48

return c

49

if c.isalpha():

49

if c.isalpha():

50

return 'x'

50

return 'x'

51

if c.isdigit():

51

if c.isdigit():

52

return 'n'

52

return 'n'

53

try:

53

try:

54

return tochr[fromc.find(c)]

54

return tochr[fromc.find(c)]

55

except (ValueError, IndexError):

55

except (ValueError, IndexError):

56

return 'o'

56

return 'o'

57

t = m.group('text')

57

t = m.group('text')

58

tt = ''.join(encodechr(i) for i in xrange(256))

58

tt = ''.join(encodechr(i) for i in xrange(256))

59

t = t.translate(tt)

59

t = t.translate(tt)

60

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

60

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

61

62

def reppython(m):

62

def reppython(m):

63

comment = m.group('comment')

63

comment = m.group('comment')

64

if comment:

64

if comment:

65

l = len(comment.rstrip())

65

l = len(comment.rstrip())

66

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

66

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

67

return repquote(m)

67

return repquote(m)

68

69

def repcomment(m):

69

def repcomment(m):

70

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

70

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

71

72

def repccomment(m):

72

def repccomment(m):

73

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

73

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

74

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

74

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

75

76

def repcallspaces(m):

76

def repcallspaces(m):

77

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

77

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

78

return m.group(1) + t

78

return m.group(1) + t

79

80

def repinclude(m):

80

def repinclude(m):

81

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

81

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

82

83

def rephere(m):

83

def rephere(m):

84

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

84

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

85

return m.group(1) + t

85

return m.group(1) + t

86

87

88

testpats = [

88

testpats = [

89

[

89

[

90

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

90

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

91

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

91

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

92

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

92

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

93

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

93

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

94

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

94

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

95

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

95

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

96

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

96

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

97

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

97

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

98

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

98

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

99

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

99

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

100

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

100

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

101

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

101

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

102

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

102

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

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

"use egrep for extended grep syntax"),

107

"use egrep for extended grep syntax"),

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

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

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

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

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

],

131

],

132

# warnings

132

# warnings

133

[

133

[

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

]

139

]

140

]

140

]

141

142

testfilters = [

142

testfilters = [

143

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

143

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

144

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

144

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

145

]

145

]

146

147

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

147

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

148

uprefix = r"^ \$ "

148

uprefix = r"^ \$ "

149

utestpats = [

149

utestpats = [

150

[

150

[

151

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

151

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

152

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

152

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

153

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

153

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

154

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

154

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

155

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

155

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

156

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

156

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

157

"explicit exit code checks unnecessary"),

157

"explicit exit code checks unnecessary"),

158

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

158

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

159

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

159

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

160

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

160

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

161

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

161

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

162

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

162

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

163

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

163

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

164

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

164

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

165

winglobmsg),

165

winglobmsg),

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

],

192

],

193

# warnings

193

# warnings

194

[

194

[

195

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

195

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

196

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

196

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

197

]

197

]

198

]

198

]

199

200

for i in [0, 1]:

200

for i in [0, 1]:

201

for tp in testpats[i]:

201

for tp in testpats[i]:

202

p = tp[0]

202

p = tp[0]

203

m = tp[1]

203

m = tp[1]

204

if p.startswith(r'^'):

204

if p.startswith(r'^'):

205

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

205

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

206

else:

206

else:

207

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

207

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

208

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

208

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

209

210

utestfilters = [

210

utestfilters = [

211

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

211

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

212

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

212

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

213

]

213

]

214

215

pypats = [

215

pypats = [

216

[

216

[

217

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

217

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

218

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

218

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

219

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

219

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

220

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

220

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

221

(r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',

221

(r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',

222

'2to3 can\'t always rewrite "import qux, foo.bar", '

222

'2to3 can\'t always rewrite "import qux, foo.bar", '

223

'use "import foo.bar" on its own line instead.'),

223

'use "import foo.bar" on its own line instead.'),

224

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

224

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

225

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

225

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

226

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

226

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

227

'dict-from-generator'),

227

'dict-from-generator'),

228

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

228

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

229

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

229

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

230

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

230

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

231

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

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

(r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),

239

(r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

"don't use camelcase in identifiers"),

245

"don't use camelcase in identifiers"),

246

246

247

"linebreak after :"),

247

"linebreak after :"),

248

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

248

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

249

r'#.*old-style'),

249

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

250

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

250

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

251

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

252

r'#.*old-style'),

251

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

253

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

252

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

254

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

253

"Python keyword is not a function"),

255

"Python keyword is not a function"),

254

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

256

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

255

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

257

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

256

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

258

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

257

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

259

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

258

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

260

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

259

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

261

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

260

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

262

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

261

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

263

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

262

"gratuitous whitespace after Python keyword"),

264

"gratuitous whitespace after Python keyword"),

263

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

265

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

264

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

266

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

265

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

267

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

266

"missing whitespace around operator"),

268

"missing whitespace around operator"),

267

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

269

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

268

"missing whitespace around operator"),

270

"missing whitespace around operator"),

269

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

271

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

270

"missing whitespace around operator"),

272

"missing whitespace around operator"),

271

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

273

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

272

"wrong whitespace around ="),

274

"wrong whitespace around ="),

273

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

275

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

274

"no whitespace around = for named parameters"),

276

"no whitespace around = for named parameters"),

275

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

277

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

276

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

278

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

277

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

279

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

278

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

280

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

279

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

281

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

280

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

282

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

281

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

283

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

282

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

284

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

283

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

285

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

284

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

286

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

285

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

287

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

286

"use opener.read() instead"),

288

"use opener.read() instead"),

287

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

289

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

288

"use opener.write() instead"),

290

"use opener.write() instead"),

289

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

291

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

290

"use util.readfile() instead"),

292

"use util.readfile() instead"),

291

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

293

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

292

"use util.writefile() instead"),

294

"use util.writefile() instead"),

293

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

295

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

294

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

296

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

295

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

297

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

296

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

298

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

297

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

299

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

298

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

300

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

299

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

301

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

300

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

302

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

301

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

303

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

302

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

304

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

303

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

305

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

304

(r'ui\.(status|progress|write|note|warn)\([\'\"]x',

306

(r'ui\.(status|progress|write|note|warn)\([\'\"]x',

305

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

307

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

306

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

308

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

307

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

309

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

308

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

310

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

309

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

311

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

310

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

312

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

311

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

313

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

312

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

314

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

313

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

315

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

314

],

316

],

315

# warnings

317

# warnings

316

[

318

[

317

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

319

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

318

]

320

]

319

]

321

]

320

322

321

pyfilters = [

323

pyfilters = [

322

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

324

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

323

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

325

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

324

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

326

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

325

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

327

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

326

]

328

]

327

329

328

txtfilters = []

330

txtfilters = []

329

331

330

txtpats = [

332

txtpats = [

331

[

333

[

332

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

334

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

333

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

335

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

334

],

336

],

335

[]

337

[]

336

]

338

]

337

339

338

cpats = [

340

cpats = [

339

[

341

[

340

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

342

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

341

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

343

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

342

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

344

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

343

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

345

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

344

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

346

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

345

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

347

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

346

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

348

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

347

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

349

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

348

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

350

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

349

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

351

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

350

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

352

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

351

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

353

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

352

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

354

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

353

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

355

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

354

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

356

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

355

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

357

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

356

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

358

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

357

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

359

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

358

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

360

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

359

],

361

],

360

# warnings

362

# warnings

361

[]

363

[]

362

]

364

]

363

365

364

cfilters = [

366

cfilters = [

365

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

367

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

366

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

368

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

367

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

369

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

368

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

370

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

369

]

371

]

370

372

371

inutilpats = [

373

inutilpats = [

372

[

374

[

373

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

375

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

374

],

376

],

375

# warnings

377

# warnings

376

[]

378

[]

377

]

379

]

378

380

379

inrevlogpats = [

381

inrevlogpats = [

380

[

382

[

381

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

383

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

382

],

384

],

383

# warnings

385

# warnings

384

[]

386

[]

385

]

387

]

386

388

387

webtemplatefilters = []

389

webtemplatefilters = []

388

390

389

webtemplatepats = [

391

webtemplatepats = [

390

[],

392

[],

391

[

393

[

392

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

394

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

393

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

395

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

394

]

396

]

395

]

397

]

396

398

397

checks = [

399

checks = [

398

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

400

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

399

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

401

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

400

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

402

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

401

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

403

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

402

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

404

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

403

pyfilters, inrevlogpats),

405

pyfilters, inrevlogpats),

404

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

406

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

405

inutilpats),

407

inutilpats),

406

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

408

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

407

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

409

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

408

webtemplatefilters, webtemplatepats),

410

webtemplatefilters, webtemplatepats),

409

]

411

]

410

412

411

def _preparepats():

413

def _preparepats():

412

for c in checks:

414

for c in checks:

413

failandwarn = c[-1]

415

failandwarn = c[-1]

414

for pats in failandwarn:

416

for pats in failandwarn:

415

for i, pseq in enumerate(pats):

417

for i, pseq in enumerate(pats):

416

# fix-up regexes for multi-line searches

418

# fix-up regexes for multi-line searches

417

p = pseq[0]

419

p = pseq[0]

418

# \s doesn't match \n

420

# \s doesn't match \n

419

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

421

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

420

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

422

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

421

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

423

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

422

424

423

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

425

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

424

filters = c[3]

426

filters = c[3]

425

for i, flt in enumerate(filters):

427

for i, flt in enumerate(filters):

426

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

428

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

427

_preparepats()

429

_preparepats()

428

430

429

class norepeatlogger(object):

431

class norepeatlogger(object):

430

def __init__(self):

432

def __init__(self):

431

self._lastseen = None

433

self._lastseen = None

432

434

433

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

435

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

434

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

436

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

435

437

436

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

438

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

437

of multiple errors.

439

of multiple errors.

438

440

439

:fname: filename

441

:fname: filename

440

:lineno: line number

442

:lineno: line number

441

:line: actual content of the line

443

:line: actual content of the line

442

:msg: error message

444

:msg: error message

443

"""

445

"""

444

msgid = fname, lineno, line

446

msgid = fname, lineno, line

445

if msgid != self._lastseen:

447

if msgid != self._lastseen:

446

if blame:

448

if blame:

447

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

449

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

448

else:

450

else:

449

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

451

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

450

print " > %s" % line

452

print " > %s" % line

451

self._lastseen = msgid

453

self._lastseen = msgid

452

print " " + msg

454

print " " + msg

453

455

454

_defaultlogger = norepeatlogger()

456

_defaultlogger = norepeatlogger()

455

457

456

def getblame(f):

458

def getblame(f):

457

lines = []

459

lines = []

458

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

460

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

459

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

461

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

460

user, rev = start.split()

462

user, rev = start.split()

461

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

463

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

462

return lines

464

return lines

463

465

464

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

466

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

465

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

467

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

466

"""checks style and portability of a given file

468

"""checks style and portability of a given file

467

469

468

:f: filepath

470

:f: filepath

469

:logfunc: function used to report error

471

:logfunc: function used to report error

470

logfunc(filename, linenumber, linecontent, errormessage)

472

logfunc(filename, linenumber, linecontent, errormessage)

471

:maxerr: number of error to display before aborting.

473

:maxerr: number of error to display before aborting.

472

Set to false (default) to report all errors

474

Set to false (default) to report all errors

473

475

474

return True if no error is found, False otherwise.

476

return True if no error is found, False otherwise.

475

"""

477

"""

476

blamecache = None

478

blamecache = None

477

result = True

479

result = True

478

480

479

try:

481

try:

480

fp = open(f)

482

fp = open(f)

481

except IOError as e:

483

except IOError as e:

482

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

484

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

483

return result

485

return result

484

pre = post = fp.read()

486

pre = post = fp.read()

485

fp.close()

487

fp.close()

486

488

487

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

489

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

488

if debug:

490

if debug:

489

print name, f

491

print name, f

490

fc = 0

492

fc = 0

491

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

493

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

492

if debug:

494

if debug:

493

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

495

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

494

name, match, f)

496

name, match, f)

495

continue

497

continue

496

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

498

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

497

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

499

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

498

# no- check- code

500

# no- check- code

499

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

501

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

500

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

502

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

501

# spelling, we write it with the expected spelling from

503

# spelling, we write it with the expected spelling from

502

# tests/test-check-code.t

504

# tests/test-check-code.t

503

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

505

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

504

return "Skip" # skip checking this file

506

return "Skip" # skip checking this file

505

for p, r in filters:

507

for p, r in filters:

506

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

508

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

507

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

509

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

508

if warnings:

510

if warnings:

509

pats = pats[0] + pats[1]

511

pats = pats[0] + pats[1]

510

else:

512

else:

511

pats = pats[0]

513

pats = pats[0]

512

# print post # uncomment to show filtered version

514

# print post # uncomment to show filtered version

513

515

514

if debug:

516

if debug:

515

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

517

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

516

518

517

prelines = None

519

prelines = None

518

errors = []

520

errors = []

519

for i, pat in enumerate(pats):

521

for i, pat in enumerate(pats):

520

if len(pat) == 3:

522

if len(pat) == 3:

521

p, msg, ignore = pat

523

p, msg, ignore = pat

522

else:

524

else:

523

p, msg = pat

525

p, msg = pat

524

ignore = None

526

ignore = None

525

if i >= nerrs:

527

if i >= nerrs:

526

msg = "warning: " + msg

528

msg = "warning: " + msg

527

529

528

pos = 0

530

pos = 0

529

n = 0

531

n = 0

530

for m in p.finditer(post):

532

for m in p.finditer(post):

531

if prelines is None:

533

if prelines is None:

532

prelines = pre.splitlines()

534

prelines = pre.splitlines()

533

postlines = post.splitlines(True)

535

postlines = post.splitlines(True)

534

536

535

start = m.start()

537

start = m.start()

536

while n < len(postlines):

538

while n < len(postlines):

537

step = len(postlines[n])

539

step = len(postlines[n])

538

if pos + step > start:

540

if pos + step > start:

539

break

541

break

540

pos += step

542

pos += step

541

n += 1

543

n += 1

542

l = prelines[n]

544

l = prelines[n]

543

545

544

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

546

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

545

if debug:

547

if debug:

546

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

548

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

547

name, f, n)

549

name, f, n)

548

continue

550

continue

549

bd = ""

551

bd = ""

550

if blame:

552

if blame:

551

bd = 'working directory'

553

bd = 'working directory'

552

if not blamecache:

554

if not blamecache:

553

blamecache = getblame(f)

555

blamecache = getblame(f)

554

if n < len(blamecache):

556

if n < len(blamecache):

555

bl, bu, br = blamecache[n]

557

bl, bu, br = blamecache[n]

556

if bl == l:

558

if bl == l:

557

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

559

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

558

560

559

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

561

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

560

result = False

562

result = False

561

563

562

errors.sort()

564

errors.sort()

563

for e in errors:

565

for e in errors:

564

logfunc(*e)

566

logfunc(*e)

565

fc += 1

567

fc += 1

566

if maxerr and fc >= maxerr:

568

if maxerr and fc >= maxerr:

567

print " (too many errors, giving up)"

569

print " (too many errors, giving up)"

568

break

570

break

569

571

570

return result

572

return result

571

573

572

if __name__ == "__main__":

574

if __name__ == "__main__":

573

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

575

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

574

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

576

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

575

help="include warning-level checks")

577

help="include warning-level checks")

576

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

578

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

577

help="max warnings per file")

579

help="max warnings per file")

578

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

580

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

579

help="use annotate to generate blame info")

581

help="use annotate to generate blame info")

580

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

582

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

581

help="show debug information")

583

help="show debug information")

582

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

584

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

583

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

585

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

584

586

585

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

587

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

586

lineno=True)

588

lineno=True)

587

(options, args) = parser.parse_args()

589

(options, args) = parser.parse_args()

588

590

589

if len(args) == 0:

591

if len(args) == 0:

590

check = glob.glob("*")

592

check = glob.glob("*")

591

else:

593

else:

592

check = args

594

check = args

593

595

594

ret = 0

596

ret = 0

595

for f in check:

597

for f in check:

596

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

598

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

597

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

599

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

598

lineno=options.lineno):

600

lineno=options.lineno):

599

ret = 1

601

ret = 1

600

sys.exit(ret)

602

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, # no-py24)
              * 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 re, glob, os, sys
             import keyword
             import optparse
             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)
             def repquote(m):
                 fromc = '.:'
                 tochr = 'pq'
                 def encodechr(i):
                     if i > 255:
                         return 'u'
                     c = chr(i)
                     if c in ' \n':
                         return c
                     if c.isalpha():
                         return 'x'
                     if c.isdigit():
                         return 'n'
                     try:
                         return tochr[fromc.find(c)]
                     except (ValueError, IndexError):
                         return 'o'
                 t = m.group('text')
                 tt = ''.join(encodechr(i) for i in xrange(256))
                 t = t.translate(tt)
                 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)', "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'ls +[^|\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"),
               ],
               # 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),
             ]
             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'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',
                  '2to3 can\'t always rewrite "import qux, foo.bar", '
                  'use "import foo.bar" on its own line instead.'),
                 (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' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),
                 (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'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)"),
+                 "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'ui\.(status|progress|write|note|warn)\([\'\"]x',
                  "missing _() in ui message (use () to hide false-positives)"),
                 (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"),
               ],
               # warnings
               [
                 (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"),
               ],
               # warnings
               []
             ]
             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:
                     fp = open(f)
                 except IOError as e:
                     print "Skipping %s, %s" % (f, str(e).split(':', 1)[0])
                     return result
                 pre = post = fp.read()
                 fp.close()
                 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)