upstream/mercurial-mirror Commit - r29217:2f9ad6ca

1

#!/usr/bin/env python

1

#!/usr/bin/env python

2

#

2

#

3

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

3

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

4

#

4

#

5

6

#

6

#

7

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

7

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

8

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

8

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

9

10

"""style and portability checker for Mercurial

10

"""style and portability checker for Mercurial

11

12

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

12

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

13

* do the work-around the rule suggests

13

* do the work-around the rule suggests

14

* doublecheck that it is a false match

14

* doublecheck that it is a false match

15

* improve the rule pattern

15

* improve the rule pattern

16

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

16

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

17

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

17

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

18

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

18

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

19

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

19

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

20

"""

20

"""

21

22

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

def opentext(f):

32

def opentext(f):

33

return open(f, encoding='ascii')

33

return open(f, encoding='ascii')

34

try:

34

try:

35

xrange

35

xrange

36

except NameError:

36

except NameError:

37

xrange = range

37

xrange = range

38

try:

38

try:

39

import re2

39

import re2

40

except ImportError:

40

except ImportError:

41

re2 = None

41

re2 = None

42

43

def compilere(pat, multiline=False):

43

def compilere(pat, multiline=False):

44

if multiline:

44

if multiline:

45

pat = '(?m)' + pat

45

pat = '(?m)' + pat

46

if re2:

46

if re2:

47

try:

47

try:

48

return re2.compile(pat)

48

return re2.compile(pat)

49

except re2.error:

49

except re2.error:

50

pass

50

pass

51

return re.compile(pat)

51

return re.compile(pat)

52

53

def repquote(m):

53

def repquote(m):

54

fromc = '.:'

54

fromc = '.:'

55

tochr = 'pq'

55

tochr = 'pq'

56

def encodechr(i):

56

def encodechr(i):

57

if i > 255:

57

if i > 255:

58

return 'u'

58

return 'u'

59

c = chr(i)

59

c = chr(i)

60

if c in ' \n':

60

if c in ' \n':

61

return c

61

return c

62

if c.isalpha():

62

if c.isalpha():

63

return 'x'

63

return 'x'

64

if c.isdigit():

64

if c.isdigit():

65

return 'n'

65

return 'n'

66

try:

66

try:

67

return tochr[fromc.find(c)]

67

return tochr[fromc.find(c)]

68

except (ValueError, IndexError):

68

except (ValueError, IndexError):

69

return 'o'

69

return 'o'

70

t = m.group('text')

70

t = m.group('text')

71

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

71

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

72

t = t.translate(tt)

72

t = t.translate(tt)

73

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

73

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

74

75

def reppython(m):

75

def reppython(m):

76

comment = m.group('comment')

76

comment = m.group('comment')

77

if comment:

77

if comment:

78

l = len(comment.rstrip())

78

l = len(comment.rstrip())

79

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

79

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

80

return repquote(m)

80

return repquote(m)

81

82

def repcomment(m):

82

def repcomment(m):

83

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

83

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

84

85

def repccomment(m):

85

def repccomment(m):

86

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

86

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

87

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

87

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

88

89

def repcallspaces(m):

89

def repcallspaces(m):

90

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

90

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

91

return m.group(1) + t

91

return m.group(1) + t

92

93

def repinclude(m):

93

def repinclude(m):

94

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

94

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

95

96

def rephere(m):

96

def rephere(m):

97

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

97

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

98

return m.group(1) + t

98

return m.group(1) + t

99

100

101

testpats = [

101

testpats = [

102

[

102

[

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

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

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

"use egrep for extended grep syntax"),

120

"use egrep for extended grep syntax"),

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

],

146

],

147

# warnings

147

# warnings

148

[

148

[

149

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

149

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

150

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

150

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

151

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

151

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

152

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

152

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

153

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

153

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

154

]

154

]

155

]

155

]

156

157

testfilters = [

157

testfilters = [

158

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

158

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

159

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

159

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

160

]

160

]

161

162

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

162

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

163

uprefix = r"^ \$ "

163

uprefix = r"^ \$ "

164

utestpats = [

164

utestpats = [

165

[

165

[

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

"explicit exit code checks unnecessary"),

172

"explicit exit code checks unnecessary"),

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

winglobmsg),

180

winglobmsg),

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

],

207

],

208

# warnings

208

# warnings

209

[

209

[

210

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

210

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

211

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

211

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

212

]

212

]

213

]

213

]

214

215

for i in [0, 1]:

215

for i in [0, 1]:

216

for tp in testpats[i]:

216

for tp in testpats[i]:

217

p = tp[0]

217

p = tp[0]

218

m = tp[1]

218

m = tp[1]

219

if p.startswith(r'^'):

219

if p.startswith(r'^'):

220

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

220

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

221

else:

221

else:

222

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

222

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

223

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

223

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

224

225

utestfilters = [

225

utestfilters = [

226

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

226

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

227

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

227

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

228

]

228

]

229

230

pypats = [

230

pypats = [

231

[

231

[

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

'dict-from-generator'),

239

'dict-from-generator'),

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

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

256

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

257

"don't use camelcase in identifiers"),

257

"don't use camelcase in identifiers"),

258

258

259

"linebreak after :"),

259

"linebreak after :"),

260

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

260

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

261

r'#.*old-style'),

261

r'#.*old-style'),

262

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

262

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

263

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

263

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

264

r'#.*old-style'),

264

r'#.*old-style'),

265

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

265

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

266

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

266

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

267

"Python keyword is not a function"),

267

"Python keyword is not a function"),

268

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

268

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

269

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

269

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

270

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

270

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

271

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

271

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

272

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

272

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

273

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

273

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

274

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

274

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

275

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

275

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

276

"gratuitous whitespace after Python keyword"),

276

"gratuitous whitespace after Python keyword"),

277

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

277

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

278

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

278

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

279

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

279

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

280

"missing whitespace around operator"),

280

"missing whitespace around operator"),

281

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

281

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

282

"missing whitespace around operator"),

282

"missing whitespace around operator"),

283

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

283

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

284

"missing whitespace around operator"),

284

"missing whitespace around operator"),

285

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

285

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

286

"wrong whitespace around ="),

286

"wrong whitespace around ="),

287

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

287

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

288

"no whitespace around = for named parameters"),

288

"no whitespace around = for named parameters"),

289

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

289

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

290

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

290

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

291

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

291

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

292

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

292

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

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

"use opener.read() instead"),

300

"use opener.read() instead"),

301

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

301

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

302

"use opener.write() instead"),

302

"use opener.write() instead"),

303

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

303

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

304

"use util.readfile() instead"),

304

"use util.readfile() instead"),

305

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

305

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

306

"use util.writefile() instead"),

306

"use util.writefile() instead"),

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

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

329

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

329

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

330

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

330

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

331

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

331

],

332

],

332

# warnings

333

# warnings

333

[

334

[

334

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

335

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

335

]

336

]

336

]

337

]

337

338

pyfilters = [

339

pyfilters = [

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

]

344

]

344

345

txtfilters = []

346

txtfilters = []

346

347

txtpats = [

348

txtpats = [

348

[

349

[

349

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

350

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

350

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

351

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

351

],

352

],

352

[]

353

[]

353

]

354

]

354

355

cpats = [

356

cpats = [

356

[

357

[

357

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

358

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

358

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

359

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

359

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

360

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

360

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

361

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

361

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

362

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

362

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

363

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

363

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

364

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

364

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

365

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

365

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

366

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

366

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

367

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

367

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

368

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

368

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

369

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

369

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

370

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

370

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

371

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

371

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

372

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

372

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

373

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

373

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

374

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

374

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

375

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

375

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

376

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

376

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

377

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

377

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

378

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

378

],

379

],

379

# warnings

380

# warnings

380

[]

381

[]

381

]

382

]

382

383

cfilters = [

384

cfilters = [

384

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

385

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

385

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

386

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

386

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

387

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

387

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

388

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

388

]

389

]

389

390

inutilpats = [

391

inutilpats = [

391

[

392

[

392

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

393

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

393

],

394

],

394

# warnings

395

# warnings

395

[]

396

[]

396

]

397

]

397

398

inrevlogpats = [

399

inrevlogpats = [

399

[

400

[

400

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

401

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

401

],

402

],

402

# warnings

403

# warnings

403

[]

404

[]

404

]

405

]

405

406

webtemplatefilters = []

407

webtemplatefilters = []

407

408

webtemplatepats = [

409

webtemplatepats = [

409

[],

410

[],

410

[

411

[

411

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

412

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

412

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

413

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

413

]

414

]

414

]

415

]

415

416

checks = [

417

checks = [

417

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

418

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

418

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

419

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

419

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

420

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

420

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

421

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

421

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

422

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

422

pyfilters, inrevlogpats),

423

pyfilters, inrevlogpats),

423

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

424

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

424

inutilpats),

425

inutilpats),

425

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

426

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

426

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

427

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

427

webtemplatefilters, webtemplatepats),

428

webtemplatefilters, webtemplatepats),

428

]

429

]

429

430

def _preparepats():

431

def _preparepats():

431

for c in checks:

432

for c in checks:

432

failandwarn = c[-1]

433

failandwarn = c[-1]

433

for pats in failandwarn:

434

for pats in failandwarn:

434

for i, pseq in enumerate(pats):

435

for i, pseq in enumerate(pats):

435

# fix-up regexes for multi-line searches

436

# fix-up regexes for multi-line searches

436

p = pseq[0]

437

p = pseq[0]

437

# \s doesn't match \n

438

# \s doesn't match \n

438

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

439

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

439

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

440

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

440

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

441

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

441

442

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

443

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

443

filters = c[3]

444

filters = c[3]

444

for i, flt in enumerate(filters):

445

for i, flt in enumerate(filters):

445

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

446

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

446

_preparepats()

447

_preparepats()

447

448

class norepeatlogger(object):

449

class norepeatlogger(object):

449

def __init__(self):

450

def __init__(self):

450

self._lastseen = None

451

self._lastseen = None

451

452

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

453

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

453

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

454

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

454

455

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

456

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

456

of multiple errors.

457

of multiple errors.

457

458

:fname: filename

459

:fname: filename

459

:lineno: line number

460

:lineno: line number

460

:line: actual content of the line

461

:line: actual content of the line

461

:msg: error message

462

:msg: error message

462

"""

463

"""

463

msgid = fname, lineno, line

464

msgid = fname, lineno, line

464

if msgid != self._lastseen:

465

if msgid != self._lastseen:

465

if blame:

466

if blame:

466

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

467

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

467

else:

468

else:

468

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

469

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

469

print(" > %s" % line)

470

print(" > %s" % line)

470

self._lastseen = msgid

471

self._lastseen = msgid

471

print(" " + msg)

472

print(" " + msg)

472

473

_defaultlogger = norepeatlogger()

474

_defaultlogger = norepeatlogger()

474

475

def getblame(f):

476

def getblame(f):

476

lines = []

477

lines = []

477

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

478

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

478

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

479

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

479

user, rev = start.split()

480

user, rev = start.split()

480

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

481

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

481

return lines

482

return lines

482

483

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

484

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

484

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

485

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

485

"""checks style and portability of a given file

486

"""checks style and portability of a given file

486

487

:f: filepath

488

:f: filepath

488

:logfunc: function used to report error

489

:logfunc: function used to report error

489

logfunc(filename, linenumber, linecontent, errormessage)

490

logfunc(filename, linenumber, linecontent, errormessage)

490

:maxerr: number of error to display before aborting.

491

:maxerr: number of error to display before aborting.

491

Set to false (default) to report all errors

492

Set to false (default) to report all errors

492

493

return True if no error is found, False otherwise.

494

return True if no error is found, False otherwise.

494

"""

495

"""

495

blamecache = None

496

blamecache = None

496

result = True

497

result = True

497

498

try:

499

try:

499

with opentext(f) as fp:

500

with opentext(f) as fp:

500

try:

501

try:

501

pre = post = fp.read()

502

pre = post = fp.read()

502

except UnicodeDecodeError as e:

503

except UnicodeDecodeError as e:

503

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

504

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

504

return result

505

return result

505

except IOError as e:

506

except IOError as e:

506

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

507

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

507

return result

508

return result

508

509

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

510

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

510

if debug:

511

if debug:

511

print(name, f)

512

print(name, f)

512

fc = 0

513

fc = 0

513

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

514

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

514

if debug:

515

if debug:

515

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

516

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

516

name, match, f))

517

name, match, f))

517

continue

518

continue

518

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

519

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

519

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

520

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

520

# no- check- code

521

# no- check- code

521

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

522

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

522

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

523

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

523

# spelling, we write it with the expected spelling from

524

# spelling, we write it with the expected spelling from

524

# tests/test-check-code.t

525

# tests/test-check-code.t

525

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

526

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

526

return "Skip" # skip checking this file

527

return "Skip" # skip checking this file

527

for p, r in filters:

528

for p, r in filters:

528

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

529

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

529

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

530

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

530

if warnings:

531

if warnings:

531

pats = pats[0] + pats[1]

532

pats = pats[0] + pats[1]

532

else:

533

else:

533

pats = pats[0]

534

pats = pats[0]

534

# print post # uncomment to show filtered version

535

# print post # uncomment to show filtered version

535

536

if debug:

537

if debug:

537

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

538

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

538

539

prelines = None

540

prelines = None

540

errors = []

541

errors = []

541

for i, pat in enumerate(pats):

542

for i, pat in enumerate(pats):

542

if len(pat) == 3:

543

if len(pat) == 3:

543

p, msg, ignore = pat

544

p, msg, ignore = pat

544

else:

545

else:

545

p, msg = pat

546

p, msg = pat

546

ignore = None

547

ignore = None

547

if i >= nerrs:

548

if i >= nerrs:

548

msg = "warning: " + msg

549

msg = "warning: " + msg

549

550

pos = 0

551

pos = 0

551

n = 0

552

n = 0

552

for m in p.finditer(post):

553

for m in p.finditer(post):

553

if prelines is None:

554

if prelines is None:

554

prelines = pre.splitlines()

555

prelines = pre.splitlines()

555

postlines = post.splitlines(True)

556

postlines = post.splitlines(True)

556

557

start = m.start()

558

start = m.start()

558

while n < len(postlines):

559

while n < len(postlines):

559

step = len(postlines[n])

560

step = len(postlines[n])

560

if pos + step > start:

561

if pos + step > start:

561

break

562

break

562

pos += step

563

pos += step

563

n += 1

564

n += 1

564

l = prelines[n]

565

l = prelines[n]

565

566

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

567

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

567

if debug:

568

if debug:

568

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

569

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

569

name, f, n))

570

name, f, n))

570

continue

571

continue

571

bd = ""

572

bd = ""

572

if blame:

573

if blame:

573

bd = 'working directory'

574

bd = 'working directory'

574

if not blamecache:

575

if not blamecache:

575

blamecache = getblame(f)

576

blamecache = getblame(f)

576

if n < len(blamecache):

577

if n < len(blamecache):

577

bl, bu, br = blamecache[n]

578

bl, bu, br = blamecache[n]

578

if bl == l:

579

if bl == l:

579

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

580

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

580

581

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

582

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

582

result = False

583

result = False

583

584

errors.sort()

585

errors.sort()

585

for e in errors:

586

for e in errors:

586

logfunc(*e)

587

logfunc(*e)

587

fc += 1

588

fc += 1

588

if maxerr and fc >= maxerr:

589

if maxerr and fc >= maxerr:

589

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

590

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

590

break

591

break

591

592

return result

593

return result

593

594

if __name__ == "__main__":

595

if __name__ == "__main__":

595

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

596

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

596

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

597

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

597

help="include warning-level checks")

598

help="include warning-level checks")

598

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

599

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

599

help="max warnings per file")

600

help="max warnings per file")

600

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

601

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

601

help="use annotate to generate blame info")

602

help="use annotate to generate blame info")

602

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

603

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

603

help="show debug information")

604

help="show debug information")

604

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

605

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

605

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

606

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

606

607

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

608

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

608

lineno=True)

609

lineno=True)

609

(options, args) = parser.parse_args()

610

(options, args) = parser.parse_args()

610

611

if len(args) == 0:

612

if len(args) == 0:

612

check = glob.glob("*")

613

check = glob.glob("*")

613

else:

614

else:

614

check = args

615

check = args

615

616

ret = 0

617

ret = 0

617

for f in check:

618

for f in check:

618

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

619

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

619

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

620

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

620

lineno=options.lineno):

621

lineno=options.lineno):

621

ret = 1

622

ret = 1

622

sys.exit(ret)

623

sys.exit(ret)

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

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

             #!/usr/bin/env python
             #
             # check-code - a style and portability checker for Mercurial
             #
             # Copyright 2010 Matt Mackall <mpm@selenic.com>
             #
             # This software may be used and distributed according to the terms of the
             # GNU General Public License version 2 or any later version.
             """style and portability checker for Mercurial
             when a rule triggers wrong, do one of the following (prefer one from top):
              * do the work-around the rule suggests
              * doublecheck that it is a false match
              * improve the rule pattern
              * add an ignore pattern to the rule (3rd arg) which matches your good line
                (you can append a short comment and match this, like: #re-raises)
              * change the pattern to a warning and list the exception in test-check-code-hg
              * ONLY use no--check-code for skipping entire files from external sources
             """
             from __future__ import absolute_import, print_function
             import glob
             import keyword
             import optparse
             import os
             import re
             import sys
             if sys.version_info[0] < 3:
                 opentext = open
             else:
                 def opentext(f):
                     return open(f, encoding='ascii')
             try:
                 xrange
             except NameError:
                 xrange = range
             try:
                 import re2
             except ImportError:
                 re2 = None
             def compilere(pat, multiline=False):
                 if multiline:
                     pat = '(?m)' + pat
                 if re2:
                     try:
                         return re2.compile(pat)
                     except re2.error:
                         pass
                 return re.compile(pat)
             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)', r"don't use 'printf \NNN', use Python"),
                 (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
                 (r'\$\(.*\)', "don't use $(expr), use `expr`"),
                 (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
                 (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                  "use egrep for extended grep syntax"),
                 (r'/bin/', "don't use explicit paths for tools"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'export .*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                 (r'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"),
                 (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
                 (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'")
               ],
               # warnings
               [
                 (r'^function', "don't use 'function', use old style"),
                 (r'^diff.*-\w*N', "don't use 'diff -N'"),
                 (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
                 (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
                 (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
               ]
             ]
             testfilters = [
                 (r"( *)(#([^\n]*\S)?)", repcomment),
                 (r"<<(\S+)((.|\n)*?\n\1)", rephere),
             ]
             winglobmsg = "use (glob) to match Windows paths too"
             uprefix = r"^  \$ "
             utestpats = [
               [
                 (r'^(\S.*||  [$>] \S.*)[ \t]\n', "trailing whitespace on non-output"),
                 (uprefix + r'.*\|\s*sed[^|>\n]*\n',
                  "use regex test output patterns instead of sed"),
                 (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
                 (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
                 (uprefix + r'.*\|\| echo.*(fail|error)',
                  "explicit exit code checks unnecessary"),
                 (uprefix + r'set -e', "don't use set -e"),
                 (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
                 (uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "
                  "as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx
                  '# no-msys'), # in test-pull.t which is skipped on windows
                 (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
                 (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
                  winglobmsg),
                 (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
                  '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
                 (r'^  reverting (?!subrepo ).*/.*[^)]$', winglobmsg),
                 (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
                 (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
                 (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
                 (r'^  moving \S+/.*[^)]$', winglobmsg),
                 (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
                 (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
                 (r'^  .*file://\$TESTTMP',
                  'write "file:/*/$TESTTMP" + (glob) to match on windows too'),
                 (r'^  (cat|find): .*: No such file or directory',
                  'use test -f to test for file existence'),
                 (r'^  diff -[^ -]*p',
                  "don't use (external) diff with -p for portability"),
                 (r'^  [-+][-+][-+] .* [-+]0000 \(glob\)',
                  "glob timezone field in diff output for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',
                  "use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N* +N* @@ (glob)' style chunk header for portability"),
                 (uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'
                  r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',
                  "use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),
               ],
               # warnings
               [
                 (r'^  [^*?/\n]* \(glob\)$',
                  "glob match with no glob character (?*/)"),
               ]
             ]
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%s)" % p[1:]
                     else:
                         p = r"^  [$>] .*(%s)" % p
                     utestpats[i].append((p, m) + tp[2:])
             utestfilters = [
                 (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
                 (r"( *)(#([^\n]*\S)?)", repcomment),
             ]
             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"),
                 (r'^import Queue', "don't use Queue, use util.queue + util.empty"),
                 (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),
                 (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
+                (r'\.next\(\)', "don't use .next(), use next(...)"),
               ],
               # 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:
                     with opentext(f) as fp:
                         try:
                             pre = post = fp.read()
                         except UnicodeDecodeError as e:
                             print("%s while reading %s" % (e, f))
                             return result
                 except IOError as e:
                     print("Skipping %s, %s" % (f, str(e).split(':', 1)[0]))
                     return result
                 for name, match, magic, filters, pats in checks:
                     if debug:
                         print(name, f)
                     fc = 0
                     if not (re.match(match, f) or (magic and re.search(magic, pre))):
                         if debug:
                             print("Skipping %s for %s it doesn't match %s" % (
                                    name, match, f))
                         continue
                     if "no-" "check-code" in pre:
                         # If you're looking at this line, it's because a file has:
                         # no- check- code
                         # but the reason to output skipping is to make life for
                         # tests easier. So, instead of writing it with a normal
                         # spelling, we write it with the expected spelling from
                         # tests/test-check-code.t
                         print("Skipping %s it has no-che?k-code (glob)" % f)
                         return "Skip" # skip checking this file
                     for p, r in filters:
                         post = re.sub(p, r, post)
                     nerrs = len(pats[0]) # nerr elements are errors
                     if warnings:
                         pats = pats[0] + pats[1]
                     else:
                         pats = pats[0]
                     # print post # uncomment to show filtered version
                     if debug:
                         print("Checking %s for %s" % (name, f))
                     prelines = None
                     errors = []
                     for i, pat in enumerate(pats):
                         if len(pat) == 3:
                             p, msg, ignore = pat
                         else:
                             p, msg = pat
                             ignore = None
                         if i >= nerrs:
                             msg = "warning: " + msg
                         pos = 0
                         n = 0
                         for m in p.finditer(post):
                             if prelines is None:
                                 prelines = pre.splitlines()
                                 postlines = post.splitlines(True)
                             start = m.start()
                             while n < len(postlines):
                                 step = len(postlines[n])
                                 if pos + step > start:
                                     break
                                 pos += step
                                 n += 1
                             l = prelines[n]
                             if ignore and re.search(ignore, l, re.MULTILINE):
                                 if debug:
                                     print("Skipping %s for %s:%s (ignore pattern)" % (
                                         name, f, n))
                                 continue
                             bd = ""
                             if blame:
                                 bd = 'working directory'
                                 if not blamecache:
                                     blamecache = getblame(f)
                                 if n < len(blamecache):
                                     bl, bu, br = blamecache[n]
                                     if bl == l:
                                         bd = '%s@%s' % (bu, br)
                             errors.append((f, lineno and n + 1, l, msg, bd))
                             result = False
                     errors.sort()
                     for e in errors:
                         logfunc(*e)
                         fc += 1
                         if maxerr and fc >= maxerr:
                             print(" (too many errors, giving up)")
                             break
                 return result
             if __name__ == "__main__":
                 parser = optparse.OptionParser("%prog [options] [files]")
                 parser.add_option("-w", "--warnings", action="store_true",
                                   help="include warning-level checks")
                 parser.add_option("-p", "--per-file", type="int",
                                   help="max warnings per file")
                 parser.add_option("-b", "--blame", action="store_true",
                                   help="use annotate to generate blame info")
                 parser.add_option("", "--debug", action="store_true",
                                   help="show debug information")
                 parser.add_option("", "--nolineno", action="store_false",
                                   dest='lineno', help="don't show line numbers")
                 parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                                     lineno=True)
                 (options, args) = parser.parse_args()
                 if len(args) == 0:
                     check = glob.glob("*")
                 else:
                     check = args
                 ret = 0
                 for f in check:
                     if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                                      blame=options.blame, debug=options.debug,
                                      lineno=options.lineno):
                         ret = 1
                 sys.exit(ret)