upstream/mercurial-mirror Commit - r28595:adda6dee

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

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

try:

29

try:

30

import re2

30

import re2

31

except ImportError:

31

except ImportError:

32

re2 = None

32

re2 = None

33

34

def compilere(pat, multiline=False):

34

def compilere(pat, multiline=False):

35

if multiline:

35

if multiline:

36

pat = '(?m)' + pat

36

pat = '(?m)' + pat

37

if re2:

37

if re2:

38

try:

38

try:

39

return re2.compile(pat)

39

return re2.compile(pat)

40

except re2.error:

40

except re2.error:

41

pass

41

pass

42

return re.compile(pat)

42

return re.compile(pat)

43

44

def repquote(m):

44

def repquote(m):

45

fromc = '.:'

45

fromc = '.:'

46

tochr = 'pq'

46

tochr = 'pq'

47

def encodechr(i):

47

def encodechr(i):

48

if i > 255:

48

if i > 255:

49

return 'u'

49

return 'u'

50

c = chr(i)

50

c = chr(i)

51

if c in ' \n':

51

if c in ' \n':

52

return c

52

return c

53

if c.isalpha():

53

if c.isalpha():

54

return 'x'

54

return 'x'

55

if c.isdigit():

55

if c.isdigit():

56

return 'n'

56

return 'n'

57

try:

57

try:

58

return tochr[fromc.find(c)]

58

return tochr[fromc.find(c)]

59

except (ValueError, IndexError):

59

except (ValueError, IndexError):

60

return 'o'

60

return 'o'

61

t = m.group('text')

61

t = m.group('text')

62

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

62

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

63

t = t.translate(tt)

63

t = t.translate(tt)

64

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

64

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

65

66

def reppython(m):

66

def reppython(m):

67

comment = m.group('comment')

67

comment = m.group('comment')

68

if comment:

68

if comment:

69

l = len(comment.rstrip())

69

l = len(comment.rstrip())

70

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

70

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

71

return repquote(m)

71

return repquote(m)

72

73

def repcomment(m):

73

def repcomment(m):

74

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

74

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

75

76

def repccomment(m):

76

def repccomment(m):

77

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

77

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

78

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

78

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

79

80

def repcallspaces(m):

80

def repcallspaces(m):

81

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

81

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

82

return m.group(1) + t

82

return m.group(1) + t

83

84

def repinclude(m):

84

def repinclude(m):

85

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

85

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

86

87

def rephere(m):

87

def rephere(m):

88

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

88

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

89

return m.group(1) + t

89

return m.group(1) + t

90

91

92

testpats = [

92

testpats = [

93

[

93

[

94

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

94

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

95

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

95

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

96

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

96

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

97

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

97

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

98

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

98

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

99

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

99

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

100

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

100

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

101

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

101

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

102

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

102

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

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

"use egrep for extended grep syntax"),

111

"use egrep for extended grep syntax"),

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

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

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

],

135

],

136

# warnings

136

# warnings

137

[

137

[

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

]

143

]

144

]

144

]

145

146

testfilters = [

146

testfilters = [

147

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

147

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

148

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

148

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

149

]

149

]

150

151

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

151

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

152

uprefix = r"^ \$ "

152

uprefix = r"^ \$ "

153

utestpats = [

153

utestpats = [

154

[

154

[

155

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

155

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

156

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

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

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

160

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

161

"explicit exit code checks unnecessary"),

161

"explicit exit code checks unnecessary"),

162

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

162

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

163

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

163

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

164

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

164

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

165

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

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

winglobmsg),

169

winglobmsg),

170

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

170

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

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

],

196

],

197

# warnings

197

# warnings

198

[

198

[

199

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

199

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

200

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

200

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

201

]

201

]

202

]

202

]

203

204

for i in [0, 1]:

204

for i in [0, 1]:

205

for tp in testpats[i]:

205

for tp in testpats[i]:

206

p = tp[0]

206

p = tp[0]

207

m = tp[1]

207

m = tp[1]

208

if p.startswith(r'^'):

208

if p.startswith(r'^'):

209

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

209

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

210

else:

210

else:

211

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

211

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

212

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

212

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

213

214

utestfilters = [

214

utestfilters = [

215

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

215

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

216

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

216

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

217

]

217

]

218

219

pypats = [

219

pypats = [

220

[

220

[

221

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

221

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

222

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

222

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

223

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

223

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

224

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

224

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

225

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

225

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

226

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

226

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

227

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

227

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

228

'dict-from-generator'),

228

'dict-from-generator'),

229

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

229

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

230

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

230

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

231

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

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

"don't use camelcase in identifiers"),

246

"don't use camelcase in identifiers"),

247

247

248

"linebreak after :"),

248

"linebreak after :"),

249

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

249

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

250

r'#.*old-style'),

250

r'#.*old-style'),

251

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

251

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

252

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

252

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

253

r'#.*old-style'),

253

r'#.*old-style'),

254

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

254

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

255

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

255

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

256

"Python keyword is not a function"),

256

"Python keyword is not a function"),

257

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

257

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

258

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

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

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

262

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

263

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

263

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

264

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

264

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

265

"gratuitous whitespace after Python keyword"),

265

"gratuitous whitespace after Python keyword"),

266

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

266

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

267

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

267

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

268

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

268

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

269

"missing whitespace around operator"),

269

"missing whitespace around operator"),

270

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

270

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

271

"missing whitespace around operator"),

271

"missing whitespace around operator"),

272

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

272

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

273

"missing whitespace around operator"),

273

"missing whitespace around operator"),

274

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

274

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

275

"wrong whitespace around ="),

275

"wrong whitespace around ="),

276

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

276

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

277

"no whitespace around = for named parameters"),

277

"no whitespace around = for named parameters"),

278

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

278

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

279

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

279

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

280

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

280

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

281

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

281

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

282

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

282

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

283

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

283

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

284

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

284

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

285

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

285

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

286

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

286

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

287

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

287

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

288

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

288

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

289

"use opener.read() instead"),

289

"use opener.read() instead"),

290

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

290

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

291

"use opener.write() instead"),

291

"use opener.write() instead"),

292

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

292

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

293

"use util.readfile() instead"),

293

"use util.readfile() instead"),

294

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

294

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

295

"use util.writefile() instead"),

295

"use util.writefile() instead"),

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

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

306

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

306

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

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

],

317

],

318

# warnings

318

# warnings

319

[

319

[

320

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

320

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

321

]

321

]

322

]

322

]

323

324

pyfilters = [

324

pyfilters = [

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

]

329

]

330

331

txtfilters = []

331

txtfilters = []

332

333

txtpats = [

333

txtpats = [

334

[

334

[

335

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

335

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

336

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

336

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

337

],

337

],

338

[]

338

[]

339

]

339

]

340

341

cpats = [

341

cpats = [

342

[

342

[

343

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

343

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

344

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

344

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

345

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

345

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

346

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

346

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

347

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

347

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

348

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

348

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

349

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

349

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

350

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

350

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

351

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

351

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

352

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

352

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

353

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

353

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

354

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

354

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

355

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

355

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

356

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

356

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

357

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

357

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

358

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

358

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

359

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

359

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

360

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

360

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

361

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

361

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

362

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

362

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

363

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

363

],

364

],

364

# warnings

365

# warnings

365

[]

366

[]

366

]

367

]

367

368

cfilters = [

369

cfilters = [

369

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

370

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

370

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

371

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

371

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

372

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

372

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

373

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

373

]

374

]

374

375

inutilpats = [

376

inutilpats = [

376

[

377

[

377

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

378

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

378

],

379

],

379

# warnings

380

# warnings

380

[]

381

[]

381

]

382

]

382

383

inrevlogpats = [

384

inrevlogpats = [

384

[

385

[

385

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

386

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

386

],

387

],

387

# warnings

388

# warnings

388

[]

389

[]

389

]

390

]

390

391

webtemplatefilters = []

392

webtemplatefilters = []

392

393

webtemplatepats = [

394

webtemplatepats = [

394

[],

395

[],

395

[

396

[

396

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

397

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

397

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

398

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

398

]

399

]

399

]

400

]

400

401

checks = [

402

checks = [

402

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

403

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

403

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

404

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

404

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

405

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

405

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

406

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

406

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

407

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

407

pyfilters, inrevlogpats),

408

pyfilters, inrevlogpats),

408

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

409

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

409

inutilpats),

410

inutilpats),

410

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

411

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

411

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

412

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

412

webtemplatefilters, webtemplatepats),

413

webtemplatefilters, webtemplatepats),

413

]

414

]

414

415

def _preparepats():

416

def _preparepats():

416

for c in checks:

417

for c in checks:

417

failandwarn = c[-1]

418

failandwarn = c[-1]

418

for pats in failandwarn:

419

for pats in failandwarn:

419

for i, pseq in enumerate(pats):

420

for i, pseq in enumerate(pats):

420

# fix-up regexes for multi-line searches

421

# fix-up regexes for multi-line searches

421

p = pseq[0]

422

p = pseq[0]

422

# \s doesn't match \n

423

# \s doesn't match \n

423

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

424

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

424

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

425

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

425

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

426

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

426

427

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

428

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

428

filters = c[3]

429

filters = c[3]

429

for i, flt in enumerate(filters):

430

for i, flt in enumerate(filters):

430

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

431

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

431

_preparepats()

432

_preparepats()

432

433

class norepeatlogger(object):

434

class norepeatlogger(object):

434

def __init__(self):

435

def __init__(self):

435

self._lastseen = None

436

self._lastseen = None

436

437

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

438

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

438

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

439

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

439

440

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

441

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

441

of multiple errors.

442

of multiple errors.

442

443

:fname: filename

444

:fname: filename

444

:lineno: line number

445

:lineno: line number

445

:line: actual content of the line

446

:line: actual content of the line

446

:msg: error message

447

:msg: error message

447

"""

448

"""

448

msgid = fname, lineno, line

449

msgid = fname, lineno, line

449

if msgid != self._lastseen:

450

if msgid != self._lastseen:

450

if blame:

451

if blame:

451

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

452

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

452

else:

453

else:

453

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

454

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

454

print(" > %s" % line)

455

print(" > %s" % line)

455

self._lastseen = msgid

456

self._lastseen = msgid

456

print(" " + msg)

457

print(" " + msg)

457

458

_defaultlogger = norepeatlogger()

459

_defaultlogger = norepeatlogger()

459

460

def getblame(f):

461

def getblame(f):

461

lines = []

462

lines = []

462

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

463

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

463

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

464

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

464

user, rev = start.split()

465

user, rev = start.split()

465

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

466

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

466

return lines

467

return lines

467

468

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

469

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

469

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

470

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

470

"""checks style and portability of a given file

471

"""checks style and portability of a given file

471

472

:f: filepath

473

:f: filepath

473

:logfunc: function used to report error

474

:logfunc: function used to report error

474

logfunc(filename, linenumber, linecontent, errormessage)

475

logfunc(filename, linenumber, linecontent, errormessage)

475

:maxerr: number of error to display before aborting.

476

:maxerr: number of error to display before aborting.

476

Set to false (default) to report all errors

477

Set to false (default) to report all errors

477

478

return True if no error is found, False otherwise.

479

return True if no error is found, False otherwise.

479

"""

480

"""

480

blamecache = None

481

blamecache = None

481

result = True

482

result = True

482

483

try:

484

try:

484

fp = open(f)

485

fp = open(f)

485

except IOError as e:

486

except IOError as e:

486

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

487

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

487

return result

488

return result

488

pre = post = fp.read()

489

pre = post = fp.read()

489

fp.close()

490

fp.close()

490

491

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

492

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

492

if debug:

493

if debug:

493

print(name, f)

494

print(name, f)

494

fc = 0

495

fc = 0

495

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

496

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

496

if debug:

497

if debug:

497

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

498

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

498

name, match, f))

499

name, match, f))

499

continue

500

continue

500

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

501

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

501

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

502

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

502

# no- check- code

503

# no- check- code

503

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

504

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

504

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

505

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

505

# spelling, we write it with the expected spelling from

506

# spelling, we write it with the expected spelling from

506

# tests/test-check-code.t

507

# tests/test-check-code.t

507

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

508

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

508

return "Skip" # skip checking this file

509

return "Skip" # skip checking this file

509

for p, r in filters:

510

for p, r in filters:

510

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

511

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

511

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

512

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

512

if warnings:

513

if warnings:

513

pats = pats[0] + pats[1]

514

pats = pats[0] + pats[1]

514

else:

515

else:

515

pats = pats[0]

516

pats = pats[0]

516

# print post # uncomment to show filtered version

517

# print post # uncomment to show filtered version

517

518

if debug:

519

if debug:

519

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

520

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

520

521

prelines = None

522

prelines = None

522

errors = []

523

errors = []

523

for i, pat in enumerate(pats):

524

for i, pat in enumerate(pats):

524

if len(pat) == 3:

525

if len(pat) == 3:

525

p, msg, ignore = pat

526

p, msg, ignore = pat

526

else:

527

else:

527

p, msg = pat

528

p, msg = pat

528

ignore = None

529

ignore = None

529

if i >= nerrs:

530

if i >= nerrs:

530

msg = "warning: " + msg

531

msg = "warning: " + msg

531

532

pos = 0

533

pos = 0

533

n = 0

534

n = 0

534

for m in p.finditer(post):

535

for m in p.finditer(post):

535

if prelines is None:

536

if prelines is None:

536

prelines = pre.splitlines()

537

prelines = pre.splitlines()

537

postlines = post.splitlines(True)

538

postlines = post.splitlines(True)

538

539

start = m.start()

540

start = m.start()

540

while n < len(postlines):

541

while n < len(postlines):

541

step = len(postlines[n])

542

step = len(postlines[n])

542

if pos + step > start:

543

if pos + step > start:

543

break

544

break

544

pos += step

545

pos += step

545

n += 1

546

n += 1

546

l = prelines[n]

547

l = prelines[n]

547

548

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

549

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

549

if debug:

550

if debug:

550

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

551

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

551

name, f, n))

552

name, f, n))

552

continue

553

continue

553

bd = ""

554

bd = ""

554

if blame:

555

if blame:

555

bd = 'working directory'

556

bd = 'working directory'

556

if not blamecache:

557

if not blamecache:

557

blamecache = getblame(f)

558

blamecache = getblame(f)

558

if n < len(blamecache):

559

if n < len(blamecache):

559

bl, bu, br = blamecache[n]

560

bl, bu, br = blamecache[n]

560

if bl == l:

561

if bl == l:

561

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

562

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

562

563

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

564

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

564

result = False

565

result = False

565

566

errors.sort()

567

errors.sort()

567

for e in errors:

568

for e in errors:

568

logfunc(*e)

569

logfunc(*e)

569

fc += 1

570

fc += 1

570

if maxerr and fc >= maxerr:

571

if maxerr and fc >= maxerr:

571

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

572

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

572

break

573

break

573

574

return result

575

return result

575

576

if __name__ == "__main__":

577

if __name__ == "__main__":

577

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

578

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

578

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

579

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

579

help="include warning-level checks")

580

help="include warning-level checks")

580

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

581

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

581

help="max warnings per file")

582

help="max warnings per file")

582

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

583

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

583

help="use annotate to generate blame info")

584

help="use annotate to generate blame info")

584

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

585

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

585

help="show debug information")

586

help="show debug information")

586

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

587

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

587

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

588

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

588

589

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

590

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

590

lineno=True)

591

lineno=True)

591

(options, args) = parser.parse_args()

592

(options, args) = parser.parse_args()

592

593

if len(args) == 0:

594

if len(args) == 0:

594

check = glob.glob("*")

595

check = glob.glob("*")

595

else:

596

else:

596

check = args

597

check = args

597

598

ret = 0

599

ret = 0

599

for f in check:

600

for f in check:

600

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

601

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

601

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

602

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

602

lineno=options.lineno):

603

lineno=options.lineno):

603

ret = 1

604

ret = 1

604

sys.exit(ret)

605

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
             """
             from __future__ import absolute_import, print_function
             import glob
             import keyword
             import optparse
             import os
             import re
             import sys
             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'(?<!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'#.*old-style'),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)",
                  r'#.*old-style'),
                 (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                                         if k not in ('print', 'exec')),
                  "Python keyword is not a function"),
                 (r',]', "unneeded trailing ',' in list"),
             #    (r'class\s[A-Z][^\(]*\((?!Exception)',
             #     "don't capitalize non-exception classes"),
             #    (r'in range\(', "use xrange"),
             #    (r'^\s*print\s+', "avoid using print in core and extensions"),
                 (r'[\x80-\xff]', "non-ASCII character literal"),
                 (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
                 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
                  "gratuitous whitespace after Python keyword"),
                 (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
             #    (r'\s\s=', "gratuitous whitespace before ="),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
                  "missing whitespace around operator"),
                 (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
                  "wrong whitespace around ="),
                 (r'\([^()]*( =[^=]|[^<>!=]= )',
                  "no whitespace around = for named parameters"),
                 (r'raise Exception', "don't raise generic exceptions"),
                 (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                  "don't use old-style two-argument raise, use Exception(message)"),
                 (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                 (r' [=!]=\s+(True|False|None)',
                  "comparison with singleton, use 'is' or 'is not' instead"),
                 (r'^\s*(while|if) [01]:',
                  "use True/False for constant Boolean expression"),
                 (r'(?:(?<!def)\s+|\()hasattr',
                  'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
                 (r'opener\([^)]*\).read\(',
                  "use opener.read() instead"),
                 (r'opener\([^)]*\).write\(',
                  "use opener.write() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.read\(',
                  "use util.readfile() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.write\(',
                  "use util.writefile() instead"),
                 (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'[\s\(](open|file)\([^)]*\)\.',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
                 (r'\.debug\(\_', "don't mark debug messages for translation"),
                 (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
                 (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
                 (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
                  'legacy exception syntax; use "as" instead of ","'),
                 (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                 (r'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"),
                 (r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),
+                (r'strcat\(', "don't use strcat"),
               ],
               # 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)