upstream/mercurial-mirror Commit - r25028:62c2786b

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

117

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

118

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

118

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

119

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

119

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

120

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

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

],

126

],

127

# warnings

127

# warnings

128

[

128

[

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

]

134

]

135

]

135

]

136

137

testfilters = [

137

testfilters = [

138

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

138

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

139

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

139

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

140

]

140

]

141

142

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

142

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

143

uprefix = r"^ \$ "

143

uprefix = r"^ \$ "

144

utestpats = [

144

utestpats = [

145

[

145

[

146

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

146

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

147

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

147

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

148

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

148

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

149

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

149

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

150

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

150

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

151

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

151

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

152

"explicit exit code checks unnecessary"),

152

"explicit exit code checks unnecessary"),

153

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

153

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

154

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

154

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

155

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

155

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

156

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

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

winglobmsg),

160

winglobmsg),

161

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

161

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

162

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

162

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

163

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

163

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

164

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

164

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

165

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

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

],

174

],

175

# warnings

175

# warnings

176

[

176

[

177

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

177

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

178

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

178

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

179

]

179

]

180

]

180

]

181

182

for i in [0, 1]:

182

for i in [0, 1]:

183

for tp in testpats[i]:

183

for tp in testpats[i]:

184

p = tp[0]

184

p = tp[0]

185

m = tp[1]

185

m = tp[1]

186

if p.startswith(r'^'):

186

if p.startswith(r'^'):

187

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

187

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

188

else:

188

else:

189

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

189

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

190

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

190

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

191

192

utestfilters = [

192

utestfilters = [

193

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

193

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

194

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

194

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

195

]

195

]

196

197

pypats = [

197

pypats = [

198

[

198

[

199

(r'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),

199

(r'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

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

207

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

208

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

208

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

209

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

209

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

210

'dict-from-generator'),

210

'dict-from-generator'),

211

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

211

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

212

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

212

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

213

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

213

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

214

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

214

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

215

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

215

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

216

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

216

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

217

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

217

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

218

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

218

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

219

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

219

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

220

(r'(\s+)try:\n((?:\n|\1\s.*\n)+?)(\1except.*?:\n'

220

(r'(\s+)try:\n((?:\n|\1\s.*\n)+?)(\1except.*?:\n'

221

r'((?:\n|\1\s.*\n)+?))+\1finally:',

221

r'((?:\n|\1\s.*\n)+?))+\1finally:',

222

'no try/except/finally in Python 2.4'),

222

'no try/except/finally in Python 2.4'),

223

(r'(?<!def)(\s+|^|$)next\(.+$',

223

(r'(?<!def)(\s+|^|$)next\(.+$',

224

'no next(foo) in Python 2.4 and 2.5, use foo.next() instead'),

224

'no next(foo) in Python 2.4 and 2.5, use foo.next() instead'),

225

(r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?'

225

(r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?'

226

r'((?:\n|\1\s.*\n)+?)\1finally:',

226

r'((?:\n|\1\s.*\n)+?)\1finally:',

227

'no yield inside try/finally in Python 2.4'),

227

'no yield inside try/finally in Python 2.4'),

228

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

228

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

229

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

229

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

230

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

230

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

231

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

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

"don't use camelcase in identifiers"),

235

"don't use camelcase in identifiers"),

236

236

237

"linebreak after :"),

237

"linebreak after :"),

238

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

238

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

239

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

239

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

240

"class foo() not available in Python 2.4, use class foo(object)"),

240

"class foo() not available in Python 2.4, use class foo(object)"),

241

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

241

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

242

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

242

"Python keyword is not a function"),

243

"Python keyword is not a function"),

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

(r'("\')\.format\(', "str.format() not available in Python 2.4"),

250

(r'("\')\.format\(', "str.format() not available in Python 2.4"),

250

(r'^\s*with\s+', "with not available in Python 2.4"),

251

(r'^\s*with\s+', "with not available in Python 2.4"),

251

(r'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"),

252

(r'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"),

252

(r'^\s*except.* as .*:', "except as not available in Python 2.4"),

253

(r'^\s*except.* as .*:', "except as not available in Python 2.4"),

253

(r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"),

254

(r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"),

254

(r'(?<!def)\s+(any|all|format)\(',

255

(r'(?<!def)\s+(any|all|format)\(',

255

"any/all/format not available in Python 2.4", 'no-py24'),

256

"any/all/format not available in Python 2.4", 'no-py24'),

256

(r'if\s.*\selse', "if ... else form not available in Python 2.4"),

257

(r'if\s.*\selse', "if ... else form not available in Python 2.4"),

257

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

258

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

258

"gratuitous whitespace after Python keyword"),

259

"gratuitous whitespace after Python keyword"),

259

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

260

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

260

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

261

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

261

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

262

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

262

"missing whitespace around operator"),

263

"missing whitespace around operator"),

263

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

264

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

264

"missing whitespace around operator"),

265

"missing whitespace around operator"),

265

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

266

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

266

"missing whitespace around operator"),

267

"missing whitespace around operator"),

267

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

268

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

268

"wrong whitespace around ="),

269

"wrong whitespace around ="),

269

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

270

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

270

"no whitespace around = for named parameters"),

271

"no whitespace around = for named parameters"),

271

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

272

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

272

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

273

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

273

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

274

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

274

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

275

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

275

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

276

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

276

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

277

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

277

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

278

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

278

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

279

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

279

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

280

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

280

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

281

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

281

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

282

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

282

"use opener.read() instead"),

283

"use opener.read() instead"),

283

(r'BaseException', 'not in Python 2.4, use Exception'),

284

(r'BaseException', 'not in Python 2.4, use Exception'),

284

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

285

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

285

"use opener.write() instead"),

286

"use opener.write() instead"),

286

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

287

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

287

"use util.readfile() instead"),

288

"use util.readfile() instead"),

288

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

289

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

289

"use util.writefile() instead"),

290

"use util.writefile() instead"),

290

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

291

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

291

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

292

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

292

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

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

],

306

],

306

# warnings

307

# warnings

307

[

308

[

308

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

309

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

309

]

310

]

310

]

311

]

311

312

pyfilters = [

313

pyfilters = [

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

]

318

]

318

319

txtfilters = []

320

txtfilters = []

320

321

txtpats = [

322

txtpats = [

322

[

323

[

323

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

324

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

324

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

325

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

325

],

326

],

326

[]

327

[]

327

]

328

]

328

329

cpats = [

330

cpats = [

330

[

331

[

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

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

337

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

337

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

338

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

338

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

339

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

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

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

344

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

344

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

345

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

345

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

346

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

346

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

347

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

347

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

348

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

348

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

349

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

349

],

350

],

350

# warnings

351

# warnings

351

[]

352

[]

352

]

353

]

353

354

cfilters = [

355

cfilters = [

355

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

356

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

356

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

357

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

357

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

358

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

358

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

359

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

359

]

360

]

360

361

inutilpats = [

362

inutilpats = [

362

[

363

[

363

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

364

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

364

],

365

],

365

# warnings

366

# warnings

366

[]

367

[]

367

]

368

]

368

369

inrevlogpats = [

370

inrevlogpats = [

370

[

371

[

371

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

372

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

372

],

373

],

373

# warnings

374

# warnings

374

[]

375

[]

375

]

376

]

376

377

webtemplatefilters = []

378

webtemplatefilters = []

378

379

webtemplatepats = [

380

webtemplatepats = [

380

[],

381

[],

381

[

382

[

382

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

383

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

383

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

384

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

384

]

385

]

385

]

386

]

386

387

checks = [

388

checks = [

388

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

389

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

389

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

390

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

390

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

391

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

391

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

392

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

392

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

393

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

393

pyfilters, inrevlogpats),

394

pyfilters, inrevlogpats),

394

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

395

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

395

inutilpats),

396

inutilpats),

396

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

397

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

397

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

398

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

398

webtemplatefilters, webtemplatepats),

399

webtemplatefilters, webtemplatepats),

399

]

400

]

400

401

def _preparepats():

402

def _preparepats():

402

for c in checks:

403

for c in checks:

403

failandwarn = c[-1]

404

failandwarn = c[-1]

404

for pats in failandwarn:

405

for pats in failandwarn:

405

for i, pseq in enumerate(pats):

406

for i, pseq in enumerate(pats):

406

# fix-up regexes for multi-line searches

407

# fix-up regexes for multi-line searches

407

p = pseq[0]

408

p = pseq[0]

408

# \s doesn't match \n

409

# \s doesn't match \n

409

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

410

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

410

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

411

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

411

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

412

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

412

413

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

414

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

414

filters = c[3]

415

filters = c[3]

415

for i, flt in enumerate(filters):

416

for i, flt in enumerate(filters):

416

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

417

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

417

_preparepats()

418

_preparepats()

418

419

class norepeatlogger(object):

420

class norepeatlogger(object):

420

def __init__(self):

421

def __init__(self):

421

self._lastseen = None

422

self._lastseen = None

422

423

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

424

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

424

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

425

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

425

426

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

427

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

427

of multiple errors.

428

of multiple errors.

428

429

:fname: filename

430

:fname: filename

430

:lineno: line number

431

:lineno: line number

431

:line: actual content of the line

432

:line: actual content of the line

432

:msg: error message

433

:msg: error message

433

"""

434

"""

434

msgid = fname, lineno, line

435

msgid = fname, lineno, line

435

if msgid != self._lastseen:

436

if msgid != self._lastseen:

436

if blame:

437

if blame:

437

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

438

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

438

else:

439

else:

439

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

440

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

440

print " > %s" % line

441

print " > %s" % line

441

self._lastseen = msgid

442

self._lastseen = msgid

442

print " " + msg

443

print " " + msg

443

444

_defaultlogger = norepeatlogger()

445

_defaultlogger = norepeatlogger()

445

446

def getblame(f):

447

def getblame(f):

447

lines = []

448

lines = []

448

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

449

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

449

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

450

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

450

user, rev = start.split()

451

user, rev = start.split()

451

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

452

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

452

return lines

453

return lines

453

454

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

455

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

455

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

456

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

456

"""checks style and portability of a given file

457

"""checks style and portability of a given file

457

458

:f: filepath

459

:f: filepath

459

:logfunc: function used to report error

460

:logfunc: function used to report error

460

logfunc(filename, linenumber, linecontent, errormessage)

461

logfunc(filename, linenumber, linecontent, errormessage)

461

:maxerr: number of error to display before aborting.

462

:maxerr: number of error to display before aborting.

462

Set to false (default) to report all errors

463

Set to false (default) to report all errors

463

464

return True if no error is found, False otherwise.

465

return True if no error is found, False otherwise.

465

"""

466

"""

466

blamecache = None

467

blamecache = None

467

result = True

468

result = True

468

469

try:

470

try:

470

fp = open(f)

471

fp = open(f)

471

except IOError, e:

472

except IOError, e:

472

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

473

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

473

return result

474

return result

474

pre = post = fp.read()

475

pre = post = fp.read()

475

fp.close()

476

fp.close()

476

477

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

478

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

478

if debug:

479

if debug:

479

print name, f

480

print name, f

480

fc = 0

481

fc = 0

481

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

482

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

482

if debug:

483

if debug:

483

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

484

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

484

name, match, f)

485

name, match, f)

485

continue

486

continue

486

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

487

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

487

print "Skipping %s it has no-" "check-code" % f

488

print "Skipping %s it has no-" "check-code" % f

488

return "Skip" # skip checking this file

489

return "Skip" # skip checking this file

489

for p, r in filters:

490

for p, r in filters:

490

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

491

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

491

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

492

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

492

if warnings:

493

if warnings:

493

pats = pats[0] + pats[1]

494

pats = pats[0] + pats[1]

494

else:

495

else:

495

pats = pats[0]

496

pats = pats[0]

496

# print post # uncomment to show filtered version

497

# print post # uncomment to show filtered version

497

498

if debug:

499

if debug:

499

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

500

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

500

501

prelines = None

502

prelines = None

502

errors = []

503

errors = []

503

for i, pat in enumerate(pats):

504

for i, pat in enumerate(pats):

504

if len(pat) == 3:

505

if len(pat) == 3:

505

p, msg, ignore = pat

506

p, msg, ignore = pat

506

else:

507

else:

507

p, msg = pat

508

p, msg = pat

508

ignore = None

509

ignore = None

509

if i >= nerrs:

510

if i >= nerrs:

510

msg = "warning: " + msg

511

msg = "warning: " + msg

511

512

pos = 0

513

pos = 0

513

n = 0

514

n = 0

514

for m in p.finditer(post):

515

for m in p.finditer(post):

515

if prelines is None:

516

if prelines is None:

516

prelines = pre.splitlines()

517

prelines = pre.splitlines()

517

postlines = post.splitlines(True)

518

postlines = post.splitlines(True)

518

519

start = m.start()

520

start = m.start()

520

while n < len(postlines):

521

while n < len(postlines):

521

step = len(postlines[n])

522

step = len(postlines[n])

522

if pos + step > start:

523

if pos + step > start:

523

break

524

break

524

pos += step

525

pos += step

525

n += 1

526

n += 1

526

l = prelines[n]

527

l = prelines[n]

527

528

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

529

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

529

if debug:

530

if debug:

530

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

531

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

531

name, f, n)

532

name, f, n)

532

continue

533

continue

533

bd = ""

534

bd = ""

534

if blame:

535

if blame:

535

bd = 'working directory'

536

bd = 'working directory'

536

if not blamecache:

537

if not blamecache:

537

blamecache = getblame(f)

538

blamecache = getblame(f)

538

if n < len(blamecache):

539

if n < len(blamecache):

539

bl, bu, br = blamecache[n]

540

bl, bu, br = blamecache[n]

540

if bl == l:

541

if bl == l:

541

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

542

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

542

543

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

544

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

544

result = False

545

result = False

545

546

errors.sort()

547

errors.sort()

547

for e in errors:

548

for e in errors:

548

logfunc(*e)

549

logfunc(*e)

549

fc += 1

550

fc += 1

550

if maxerr and fc >= maxerr:

551

if maxerr and fc >= maxerr:

551

print " (too many errors, giving up)"

552

print " (too many errors, giving up)"

552

break

553

break

553

554

return result

555

return result

555

556

if __name__ == "__main__":

557

if __name__ == "__main__":

557

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

558

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

558

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

559

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

559

help="include warning-level checks")

560

help="include warning-level checks")

560

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

561

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

561

help="max warnings per file")

562

help="max warnings per file")

562

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

563

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

563

help="use annotate to generate blame info")

564

help="use annotate to generate blame info")

564

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

565

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

565

help="show debug information")

566

help="show debug information")

566

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

567

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

567

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

568

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

568

569

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

570

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

570

lineno=True)

571

lineno=True)

571

(options, args) = parser.parse_args()

572

(options, args) = parser.parse_args()

572

573

if len(args) == 0:

574

if len(args) == 0:

574

check = glob.glob("*")

575

check = glob.glob("*")

575

else:

576

else:

576

check = args

577

check = args

577

578

ret = 0

579

ret = 0

579

for f in check:

580

for f in check:

580

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

581

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

581

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

582

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

582

lineno=options.lineno):

583

lineno=options.lineno):

583

ret = 1

584

ret = 1

584

sys.exit(ret)

585

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'^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*u.*$\n(^  \$ |^$)', "prefix diff -u with cmp"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py")
               ],
               # 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.*||  [$>] .*)[ \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'),
               ],
               # 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'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),
                 (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'(\s+)try:\n((?:\n|\1\s.*\n)+?)(\1except.*?:\n'
                  r'((?:\n|\1\s.*\n)+?))+\1finally:',
                  'no try/except/finally in Python 2.4'),
                 (r'(?<!def)(\s+|^|\()next\(.+\)',
                  'no next(foo) in Python 2.4 and 2.5, use foo.next() instead'),
                 (r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?'
                  r'((?:\n|\1\s.*\n)+?)\1finally:',
                  'no yield inside try/finally in Python 2.4'),
                 (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]+\(\):',
                  "class foo() not available in Python 2.4, use class foo(object)"),
-                (r'\b(%s)\(' % '|'.join(keyword.kwlist),
+                (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() not available in Python 2.4"),
                 (r'^\s*with\s+', "with not available in Python 2.4"),
                 (r'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"),
                 (r'^\s*except.* as .*:', "except as not available in Python 2.4"),
                 (r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"),
                 (r'(?<!def)\s+(any|all|format)\(',
                  "any/all/format not available in Python 2.4", 'no-py24'),
                 (r'if\s.*\selse', "if ... else form not available in Python 2.4"),
                 (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'BaseException', 'not in Python 2.4, use Exception'),
                 (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':\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, '')"),
               ],
               # 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'^#\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, 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, f))):
                         if debug:
                             print "Skipping %s for %s it doesn't match %s" % (
                                    name, match, f)
                         continue
                     if "no-" "check-code" in pre:
                         print "Skipping %s it has no-" "check-code" % 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)