upstream/mercurial-mirror Commit - r30557:cbeb54ec

1

#!/usr/bin/env python

1

#!/usr/bin/env python

2

#

2

#

3

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

3

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

4

#

4

#

5

6

#

6

#

7

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

7

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

8

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

8

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

9

10

"""style and portability checker for Mercurial

10

"""style and portability checker for Mercurial

11

12

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

12

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

13

* do the work-around the rule suggests

13

* do the work-around the rule suggests

14

* doublecheck that it is a false match

14

* doublecheck that it is a false match

15

* improve the rule pattern

15

* improve the rule pattern

16

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

16

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

17

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

17

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

18

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

18

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

19

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

19

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

20

"""

20

"""

21

22

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

def opentext(f):

32

def opentext(f):

33

return open(f, encoding='ascii')

33

return open(f, encoding='ascii')

34

try:

34

try:

35

xrange

35

xrange

36

except NameError:

36

except NameError:

37

xrange = range

37

xrange = range

38

try:

38

try:

39

import re2

39

import re2

40

except ImportError:

40

except ImportError:

41

re2 = None

41

re2 = None

42

43

def compilere(pat, multiline=False):

43

def compilere(pat, multiline=False):

44

if multiline:

44

if multiline:

45

pat = '(?m)' + pat

45

pat = '(?m)' + pat

46

if re2:

46

if re2:

47

try:

47

try:

48

return re2.compile(pat)

48

return re2.compile(pat)

49

except re2.error:

49

except re2.error:

50

pass

50

pass

51

return re.compile(pat)

51

return re.compile(pat)

52

53

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

53

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

54

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

54

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

55

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

55

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

56

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

56

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

57

def _repquoteencodechr(i):

57

def _repquoteencodechr(i):

58

if i > 255:

58

if i > 255:

59

return 'u'

59

return 'u'

60

c = chr(i)

60

c = chr(i)

61

if c in _repquotefixedmap:

61

if c in _repquotefixedmap:

62

return _repquotefixedmap[c]

62

return _repquotefixedmap[c]

63

if c.isalpha():

63

if c.isalpha():

64

return 'x'

64

return 'x'

65

if c.isdigit():

65

if c.isdigit():

66

return 'n'

66

return 'n'

67

return 'o'

67

return 'o'

68

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

68

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

69

70

def repquote(m):

70

def repquote(m):

71

t = m.group('text')

71

t = m.group('text')

72

t = t.translate(_repquotett)

72

t = t.translate(_repquotett)

73

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

73

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

74

75

def reppython(m):

75

def reppython(m):

76

comment = m.group('comment')

76

comment = m.group('comment')

77

if comment:

77

if comment:

78

l = len(comment.rstrip())

78

l = len(comment.rstrip())

79

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

79

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

80

return repquote(m)

80

return repquote(m)

81

82

def repcomment(m):

82

def repcomment(m):

83

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

83

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

84

85

def repccomment(m):

85

def repccomment(m):

86

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

86

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

87

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

87

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

88

89

def repcallspaces(m):

89

def repcallspaces(m):

90

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

90

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

91

return m.group(1) + t

91

return m.group(1) + t

92

93

def repinclude(m):

93

def repinclude(m):

94

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

94

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

95

96

def rephere(m):

96

def rephere(m):

97

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

97

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

98

return m.group(1) + t

98

return m.group(1) + t

99

100

101

testpats = [

101

testpats = [

102

[

102

[

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

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

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

"use egrep for extended grep syntax"),

120

"use egrep for extended grep syntax"),

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

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

144

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

145

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

145

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

146

(r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),

146

],

147

],

147

# warnings

148

# warnings

148

[

149

[

149

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

150

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

150

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

151

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

151

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

152

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

152

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

153

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

153

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

154

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

154

]

155

]

155

]

156

]

156

157

testfilters = [

158

testfilters = [

158

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

159

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

159

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

160

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

160

]

161

]

161

162

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

163

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

163

uprefix = r"^ \$ "

164

uprefix = r"^ \$ "

164

utestpats = [

165

utestpats = [

165

[

166

[

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

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

172

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

172

"explicit exit code checks unnecessary"),

173

"explicit exit code checks unnecessary"),

173

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

174

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

174

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

175

(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 "

176

(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

177

"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

178

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

178

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

179

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

179

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

180

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

180

winglobmsg),

181

winglobmsg),

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

(r'^ [^$>].*27\.0\.0\.1.*[^)]$',

193

(r'^ [^$>].*27\.0\.0\.1.*[^)]$',

193

'use (glob) to match localhost IP on hosts without 127.0.0.1 too'),

194

'use (glob) to match localhost IP on hosts without 127.0.0.1 too'),

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

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

207

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

207

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

208

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

208

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

209

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

209

],

210

],

210

# warnings

211

# warnings

211

[

212

[

212

(r'^ (?!.*127\.0\.0\.1)[^*?/\n]* $glob$$',

213

(r'^ (?!.*127\.0\.0\.1)[^*?/\n]* $glob$$',

213

"glob match with no glob string (?, *, /, and 127.0.0.1)"),

214

"glob match with no glob string (?, *, /, and 127.0.0.1)"),

214

]

215

]

215

]

216

]

216

217

for i in [0, 1]:

218

for i in [0, 1]:

218

for tp in testpats[i]:

219

for tp in testpats[i]:

219

p = tp[0]

220

p = tp[0]

220

m = tp[1]

221

m = tp[1]

221

if p.startswith(r'^'):

222

if p.startswith(r'^'):

222

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

223

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

223

else:

224

else:

224

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

225

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

225

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

226

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

226

227

utestfilters = [

228

utestfilters = [

228

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

229

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

229

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

230

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

230

]

231

]

231

232

pypats = [

233

pypats = [

233

[

234

[

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

'dict-from-generator'),

242

'dict-from-generator'),

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

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

256

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

256

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

257

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

257

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

258

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

258

"don't use camelcase in identifiers"),

259

"don't use camelcase in identifiers"),

259

260

260

"linebreak after :"),

261

"linebreak after :"),

261

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

262

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

262

r'#.*old-style'),

263

r'#.*old-style'),

263

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

264

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

264

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

265

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

265

r'#.*old-style'),

266

r'#.*old-style'),

266

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

267

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

267

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

268

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

268

"Python keyword is not a function"),

269

"Python keyword is not a function"),

269

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

270

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

270

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

271

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

271

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

272

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

272

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

273

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

273

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

274

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

274

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

275

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

275

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

276

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

276

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

277

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

277

"gratuitous whitespace after Python keyword"),

278

"gratuitous whitespace after Python keyword"),

278

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

279

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

279

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

280

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

280

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

281

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

281

"missing whitespace around operator"),

282

"missing whitespace around operator"),

282

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

283

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

283

"missing whitespace around operator"),

284

"missing whitespace around operator"),

284

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

285

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

285

"missing whitespace around operator"),

286

"missing whitespace around operator"),

286

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

287

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

287

"wrong whitespace around ="),

288

"wrong whitespace around ="),

288

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

289

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

289

"no whitespace around = for named parameters"),

290

"no whitespace around = for named parameters"),

290

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

291

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

291

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

292

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

292

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

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

"use opener.read() instead"),

302

"use opener.read() instead"),

302

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

303

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

303

"use opener.write() instead"),

304

"use opener.write() instead"),

304

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

305

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

305

"use util.readfile() instead"),

306

"use util.readfile() instead"),

306

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

307

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

307

"use util.writefile() instead"),

308

"use util.writefile() instead"),

308

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

309

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

309

"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"),

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

(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"'),

324

# 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

325

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

326

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

326

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

327

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

327

(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"),

328

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

329

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

329

(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"),

330

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

331

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

331

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

332

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

332

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

333

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

333

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

334

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

334

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

335

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

335

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

336

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

336

(r'^import BaseHTTPServer', "use util.httpserver instead"),

337

(r'^import BaseHTTPServer', "use util.httpserver instead"),

337

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

338

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

338

339

# rules depending on implementation of repquote()

340

# rules depending on implementation of repquote()

340

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

341

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

341

'string join across lines with no space'),

342

'string join across lines with no space'),

342

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

343

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

343

[ \t\n#]*

344

[ \t\n#]*

344

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

345

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

345

# contains translatable message)

346

# contains translatable message)

346

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

347

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

347

(?# sequence consisting of below might precede translatable message

348

(?# sequence consisting of below might precede translatable message

348

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

349

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

349

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

350

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

350

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

351

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

351

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

352

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

352

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

353

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

353

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

354

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

354

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

355

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

355

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

356

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

356

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

357

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

357

],

358

],

358

# warnings

359

# warnings

359

[

360

[

360

# rules depending on implementation of repquote()

361

# rules depending on implementation of repquote()

361

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

362

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

362

]

363

]

363

]

364

]

364

365

pyfilters = [

366

pyfilters = [

366

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

367

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

367

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

368

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

368

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

369

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

369

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

370

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

370

]

371

]

371

372

txtfilters = []

373

txtfilters = []

373

374

txtpats = [

375

txtpats = [

375

[

376

[

376

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

377

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

377

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

378

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

378

],

379

],

379

[]

380

[]

380

]

381

]

381

382

cpats = [

383

cpats = [

383

[

384

[

384

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

385

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

385

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

386

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

386

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

387

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

387

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

388

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

388

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

389

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

389

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

390

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

390

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

391

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

391

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

392

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

392

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

393

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

393

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

394

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

394

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

395

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

395

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

396

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

396

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

397

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

397

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

398

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

398

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

399

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

399

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

400

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

400

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

401

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

401

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

402

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

402

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

403

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

403

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

404

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

404

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

405

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

405

406

# rules depending on implementation of repquote()

407

# rules depending on implementation of repquote()

407

],

408

],

408

# warnings

409

# warnings

409

[

410

[

410

# rules depending on implementation of repquote()

411

# rules depending on implementation of repquote()

411

]

412

]

412

]

413

]

413

414

cfilters = [

415

cfilters = [

415

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

416

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

416

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

417

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

417

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

418

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

418

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

419

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

419

]

420

]

420

421

inutilpats = [

422

inutilpats = [

422

[

423

[

423

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

424

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

424

],

425

],

425

# warnings

426

# warnings

426

[]

427

[]

427

]

428

]

428

429

inrevlogpats = [

430

inrevlogpats = [

430

[

431

[

431

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

432

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

432

],

433

],

433

# warnings

434

# warnings

434

[]

435

[]

435

]

436

]

436

437

webtemplatefilters = []

438

webtemplatefilters = []

438

439

webtemplatepats = [

440

webtemplatepats = [

440

[],

441

[],

441

[

442

[

442

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

443

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

443

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

444

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

444

]

445

]

445

]

446

]

446

447

allfilesfilters = []

448

allfilesfilters = []

448

449

allfilespats = [

450

allfilespats = [

450

[

451

[

451

(r'(http|https)://[a-zA-Z0-9./]*selenic.com/',

452

(r'(http|https)://[a-zA-Z0-9./]*selenic.com/',

452

'use mercurial-scm.org domain URL'),

453

'use mercurial-scm.org domain URL'),

453

],

454

],

454

# warnings

455

# warnings

455

[],

456

[],

456

]

457

]

457

458

checks = [

459

checks = [

459

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

460

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

460

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

461

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

461

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

462

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

462

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

463

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

463

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

464

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

464

pyfilters, inrevlogpats),

465

pyfilters, inrevlogpats),

465

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

466

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

466

inutilpats),

467

inutilpats),

467

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

468

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

468

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

469

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

469

webtemplatefilters, webtemplatepats),

470

webtemplatefilters, webtemplatepats),

470

('all except for .po', r'.*(?<!\.po)$', '',

471

('all except for .po', r'.*(?<!\.po)$', '',

471

allfilesfilters, allfilespats),

472

allfilesfilters, allfilespats),

472

]

473

]

473

474

def _preparepats():

475

def _preparepats():

475

for c in checks:

476

for c in checks:

476

failandwarn = c[-1]

477

failandwarn = c[-1]

477

for pats in failandwarn:

478

for pats in failandwarn:

478

for i, pseq in enumerate(pats):

479

for i, pseq in enumerate(pats):

479

# fix-up regexes for multi-line searches

480

# fix-up regexes for multi-line searches

480

p = pseq[0]

481

p = pseq[0]

481

# \s doesn't match \n

482

# \s doesn't match \n

482

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

483

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

483

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

484

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

484

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

485

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

485

486

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

487

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

487

filters = c[3]

488

filters = c[3]

488

for i, flt in enumerate(filters):

489

for i, flt in enumerate(filters):

489

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

490

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

490

491

class norepeatlogger(object):

492

class norepeatlogger(object):

492

def __init__(self):

493

def __init__(self):

493

self._lastseen = None

494

self._lastseen = None

494

495

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

496

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

496

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

497

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

497

498

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

499

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

499

of multiple errors.

500

of multiple errors.

500

501

:fname: filename

502

:fname: filename

502

:lineno: line number

503

:lineno: line number

503

:line: actual content of the line

504

:line: actual content of the line

504

:msg: error message

505

:msg: error message

505

"""

506

"""

506

msgid = fname, lineno, line

507

msgid = fname, lineno, line

507

if msgid != self._lastseen:

508

if msgid != self._lastseen:

508

if blame:

509

if blame:

509

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

510

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

510

else:

511

else:

511

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

512

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

512

print(" > %s" % line)

513

print(" > %s" % line)

513

self._lastseen = msgid

514

self._lastseen = msgid

514

print(" " + msg)

515

print(" " + msg)

515

516

_defaultlogger = norepeatlogger()

517

_defaultlogger = norepeatlogger()

517

518

def getblame(f):

519

def getblame(f):

519

lines = []

520

lines = []

520

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

521

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

521

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

522

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

522

user, rev = start.split()

523

user, rev = start.split()

523

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

524

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

524

return lines

525

return lines

525

526

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

527

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

527

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

528

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

528

"""checks style and portability of a given file

529

"""checks style and portability of a given file

529

530

:f: filepath

531

:f: filepath

531

:logfunc: function used to report error

532

:logfunc: function used to report error

532

logfunc(filename, linenumber, linecontent, errormessage)

533

logfunc(filename, linenumber, linecontent, errormessage)

533

:maxerr: number of error to display before aborting.

534

:maxerr: number of error to display before aborting.

534

Set to false (default) to report all errors

535

Set to false (default) to report all errors

535

536

return True if no error is found, False otherwise.

537

return True if no error is found, False otherwise.

537

"""

538

"""

538

blamecache = None

539

blamecache = None

539

result = True

540

result = True

540

541

try:

542

try:

542

with opentext(f) as fp:

543

with opentext(f) as fp:

543

try:

544

try:

544

pre = post = fp.read()

545

pre = post = fp.read()

545

except UnicodeDecodeError as e:

546

except UnicodeDecodeError as e:

546

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

547

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

547

return result

548

return result

548

except IOError as e:

549

except IOError as e:

549

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

550

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

550

return result

551

return result

551

552

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

553

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

553

post = pre # discard filtering result of previous check

554

post = pre # discard filtering result of previous check

554

if debug:

555

if debug:

555

print(name, f)

556

print(name, f)

556

fc = 0

557

fc = 0

557

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

558

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

558

if debug:

559

if debug:

559

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

560

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

560

name, match, f))

561

name, match, f))

561

continue

562

continue

562

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

563

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

563

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

564

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

564

# no- check- code

565

# no- check- code

565

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

566

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

566

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

567

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

567

# spelling, we write it with the expected spelling from

568

# spelling, we write it with the expected spelling from

568

# tests/test-check-code.t

569

# tests/test-check-code.t

569

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

570

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

570

return "Skip" # skip checking this file

571

return "Skip" # skip checking this file

571

for p, r in filters:

572

for p, r in filters:

572

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

573

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

573

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

574

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

574

if warnings:

575

if warnings:

575

pats = pats[0] + pats[1]

576

pats = pats[0] + pats[1]

576

else:

577

else:

577

pats = pats[0]

578

pats = pats[0]

578

# print post # uncomment to show filtered version

579

# print post # uncomment to show filtered version

579

580

if debug:

581

if debug:

581

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

582

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

582

583

prelines = None

584

prelines = None

584

errors = []

585

errors = []

585

for i, pat in enumerate(pats):

586

for i, pat in enumerate(pats):

586

if len(pat) == 3:

587

if len(pat) == 3:

587

p, msg, ignore = pat

588

p, msg, ignore = pat

588

else:

589

else:

589

p, msg = pat

590

p, msg = pat

590

ignore = None

591

ignore = None

591

if i >= nerrs:

592

if i >= nerrs:

592

msg = "warning: " + msg

593

msg = "warning: " + msg

593

594

pos = 0

595

pos = 0

595

n = 0

596

n = 0

596

for m in p.finditer(post):

597

for m in p.finditer(post):

597

if prelines is None:

598

if prelines is None:

598

prelines = pre.splitlines()

599

prelines = pre.splitlines()

599

postlines = post.splitlines(True)

600

postlines = post.splitlines(True)

600

601

start = m.start()

602

start = m.start()

602

while n < len(postlines):

603

while n < len(postlines):

603

step = len(postlines[n])

604

step = len(postlines[n])

604

if pos + step > start:

605

if pos + step > start:

605

break

606

break

606

pos += step

607

pos += step

607

n += 1

608

n += 1

608

l = prelines[n]

609

l = prelines[n]

609

610

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

611

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

611

if debug:

612

if debug:

612

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

613

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

613

name, f, n))

614

name, f, n))

614

continue

615

continue

615

bd = ""

616

bd = ""

616

if blame:

617

if blame:

617

bd = 'working directory'

618

bd = 'working directory'

618

if not blamecache:

619

if not blamecache:

619

blamecache = getblame(f)

620

blamecache = getblame(f)

620

if n < len(blamecache):

621

if n < len(blamecache):

621

bl, bu, br = blamecache[n]

622

bl, bu, br = blamecache[n]

622

if bl == l:

623

if bl == l:

623

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

624

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

624

625

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

626

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

626

result = False

627

result = False

627

628

errors.sort()

629

errors.sort()

629

for e in errors:

630

for e in errors:

630

logfunc(*e)

631

logfunc(*e)

631

fc += 1

632

fc += 1

632

if maxerr and fc >= maxerr:

633

if maxerr and fc >= maxerr:

633

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

634

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

634

break

635

break

635

636

return result

637

return result

637

638

def main():

639

def main():

639

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

640

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

640

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

641

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

641

help="include warning-level checks")

642

help="include warning-level checks")

642

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

643

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

643

help="max warnings per file")

644

help="max warnings per file")

644

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

645

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

645

help="use annotate to generate blame info")

646

help="use annotate to generate blame info")

646

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

647

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

647

help="show debug information")

648

help="show debug information")

648

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

649

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

649

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

650

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

650

651

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

652

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

652

lineno=True)

653

lineno=True)

653

(options, args) = parser.parse_args()

654

(options, args) = parser.parse_args()

654

655

if len(args) == 0:

656

if len(args) == 0:

656

check = glob.glob("*")

657

check = glob.glob("*")

657

else:

658

else:

658

check = args

659

check = args

659

660

_preparepats()

661

_preparepats()

661

662

ret = 0

663

ret = 0

663

for f in check:

664

for f in check:

664

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

665

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

665

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

666

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

666

lineno=options.lineno):

667

lineno=options.lineno):

667

ret = 1

668

ret = 1

668

return ret

669

return ret

669

670

if __name__ == "__main__":

671

if __name__ == "__main__":

671

sys.exit(main())

672

sys.exit(main())

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

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

             #!/usr/bin/env python
             #
             # check-code - a style and portability checker for Mercurial
             #
             # Copyright 2010 Matt Mackall <mpm@selenic.com>
             #
             # This software may be used and distributed according to the terms of the
             # GNU General Public License version 2 or any later version.
             """style and portability checker for Mercurial
             when a rule triggers wrong, do one of the following (prefer one from top):
              * do the work-around the rule suggests
              * doublecheck that it is a false match
              * improve the rule pattern
              * add an ignore pattern to the rule (3rd arg) which matches your good line
                (you can append a short comment and match this, like: #re-raises)
              * change the pattern to a warning and list the exception in test-check-code-hg
              * ONLY use no--check-code for skipping entire files from external sources
             """
             from __future__ import absolute_import, print_function
             import glob
             import keyword
             import optparse
             import os
             import re
             import sys
             if sys.version_info[0] < 3:
                 opentext = open
             else:
                 def opentext(f):
                     return open(f, encoding='ascii')
             try:
                 xrange
             except NameError:
                 xrange = range
             try:
                 import re2
             except ImportError:
                 re2 = None
             def compilere(pat, multiline=False):
                 if multiline:
                     pat = '(?m)' + pat
                 if re2:
                     try:
                         return re2.compile(pat)
                     except re2.error:
                         pass
                 return re.compile(pat)
             # check "rules depending on implementation of repquote()" in each
             # patterns (especially pypats), before changing around repquote()
             _repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
                                  '%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}
             def _repquoteencodechr(i):
                 if i > 255:
                     return 'u'
                 c = chr(i)
                 if c in _repquotefixedmap:
                     return _repquotefixedmap[c]
                 if c.isalpha():
                     return 'x'
                 if c.isdigit():
                     return 'n'
                 return 'o'
             _repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))
             def repquote(m):
                 t = m.group('text')
                 t = t.translate(_repquotett)
                 return m.group('quote') + t + m.group('quote')
             def reppython(m):
                 comment = m.group('comment')
                 if comment:
                     l = len(comment.rstrip())
                     return "#" * l + comment[l:]
                 return repquote(m)
             def repcomment(m):
                 return m.group(1) + "#" * len(m.group(2))
             def repccomment(m):
                 t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
                 return m.group(1) + t + "*/"
             def repcallspaces(m):
                 t = re.sub(r"\n\s+", "\n", m.group(2))
                 return m.group(1) + t
             def repinclude(m):
                 return m.group(1) + "<foo>"
             def rephere(m):
                 t = re.sub(r"\S", "x", m.group(2))
                 return m.group(1) + t
             testpats = [
               [
                 (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),
                 (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
                 (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
                 (r'(?<!hg )grep.* -a', "don't use 'grep -a', use in-line python"),
                 (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
                 (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
                 (r'echo -n', "don't use 'echo -n', use printf"),
                 (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
                 (r'head -c', "don't use 'head -c', use 'dd'"),
                 (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
                 (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
                 (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
                 (r'printf.*[^\\]\\([1-9]|0\d)', r"don't use 'printf \NNN', use Python"),
                 (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
                 (r'\$\(.*\)', "don't use $(expr), use `expr`"),
                 (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
                 (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                  "use egrep for extended grep syntax"),
                 (r'/bin/', "don't use explicit paths for tools"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'export .*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                 (r'\bls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
                 (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
                 (r'^stop\(\)', "don't use 'stop' as a shell function name"),
                 (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
                 (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
                 (r'^alias\b.*=', "don't use alias, use a function"),
                 (r'if\s*!', "don't use '!' to negate exit status"),
                 (r'/dev/u?random', "don't use entropy, use /dev/zero"),
                 (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
                 (r'^( *)\t', "don't use tabs to indent"),
                 (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
                  "put a backslash-escaped newline after sed 'i' command"),
                 (r'^diff *-\w*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
                 (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'\|&', "don't use |&, use 2>&1"),
                 (r'\w =  +\w', "only one space after = allowed"),
                 (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
-                (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'")
+                (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'"),
+                (r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),
               ],
               # 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'^  [^$>].*27\.0\.0\.1.*[^)]$',
                  'use (glob) to match localhost IP on hosts without 127.0.0.1 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'^  (?!.*127\.0\.0\.1)[^*?/\n]* \(glob\)$',
                  "glob match with no glob string (?, *, /, and 127.0.0.1)"),
               ]
             ]
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%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'\bdict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
                  'dict-from-generator'),
                 (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
                 (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
                 (r'^\s*\t', "don't use tabs"),
                 (r'\S;\s*\n', "semicolon"),
                 (r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
                 (r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
                 (r'(\w|\)),\w', "missing whitespace after ,"),
                 (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
                 (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
                 (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'.{81}', "line too long"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
             #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
             #     "don't use underbars in identifiers"),
                 (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
                  "don't use camelcase in identifiers"),
                 (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                  "linebreak after :"),
                 (r'class\s[^( \n]+:', "old-style class, use class foo(object)",
                  r'#.*old-style'),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)",
                  r'#.*old-style'),
                 (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                                         if k not in ('print', 'exec')),
                  "Python keyword is not a function"),
                 (r',]', "unneeded trailing ',' in list"),
             #    (r'class\s[A-Z][^\(]*\((?!Exception)',
             #     "don't capitalize non-exception classes"),
             #    (r'in range\(', "use xrange"),
             #    (r'^\s*print\s+', "avoid using print in core and extensions"),
                 (r'[\x80-\xff]', "non-ASCII character literal"),
                 (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
                 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
                  "gratuitous whitespace after Python keyword"),
                 (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
             #    (r'\s\s=', "gratuitous whitespace before ="),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
                  "missing whitespace around operator"),
                 (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
                  "wrong whitespace around ="),
                 (r'\([^()]*( =[^=]|[^<>!=]= )',
                  "no whitespace around = for named parameters"),
                 (r'raise Exception', "don't raise generic exceptions"),
                 (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                  "don't use old-style two-argument raise, use Exception(message)"),
                 (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                 (r' [=!]=\s+(True|False|None)',
                  "comparison with singleton, use 'is' or 'is not' instead"),
                 (r'^\s*(while|if) [01]:',
                  "use True/False for constant Boolean expression"),
                 (r'(?:(?<!def)\s+|\()hasattr\(',
                  'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
                 (r'opener\([^)]*\).read\(',
                  "use opener.read() instead"),
                 (r'opener\([^)]*\).write\(',
                  "use opener.write() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.read\(',
                  "use util.readfile() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.write\(',
                  "use util.writefile() instead"),
                 (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'[\s\(](open|file)\([^)]*\)\.',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
                 (r'\.debug\(\_', "don't mark debug messages for translation"),
                 (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
                 (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
                 (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
                  'legacy exception syntax; use "as" instead of ","'),
                 (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                 (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
                 (r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
                 (r'os\.path\.join\(.*, *(""|\'\')\)',
                  "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
                 (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
                 # XXX only catch mutable arguments on the first line of the definition
                 (r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'^import Queue', "don't use Queue, use util.queue + util.empty"),
                 (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),
                 (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
                 (r'^import SocketServer', "don't use SockerServer, use util.socketserver"),
                 (r'^import urlparse', "don't use urlparse, use util.urlparse"),
                 (r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),
                 (r'^import cPickle', "don't use cPickle, use util.pickle"),
                 (r'^import pickle', "don't use pickle, use util.pickle"),
                 (r'^import httplib', "don't use httplib, use util.httplib"),
                 (r'^import BaseHTTPServer', "use util.httpserver instead"),
                 (r'\.next\(\)', "don't use .next(), use next(...)"),
                 # rules depending on implementation of repquote()
                 (r' x+[xpqo%APM][\'"]\n\s+[\'"]x',
                  'string join across lines with no space'),
                 (r'''(?x)ui\.(status|progress|write|note|warn)\(
                      [ \t\n#]*
                      (?# any strings/comments might precede a string, which
                        # contains translatable message)
                      ((['"]|\'\'\'|""")[ \npq%bAPMxno]*(['"]|\'\'\'|""")[ \t\n#]+)*
                      (?# sequence consisting of below might precede translatable message
                        # - formatting string: "% 10s", "%05d", "% -3.2f", "%*s", "%%" ...
                        # - escaped character: "\\", "\n", "\0" ...
                        # - character other than '%', 'b' as '\', and 'x' as alphabet)
                      (['"]|\'\'\'|""")
                      ((%([ n]?[PM]?([np]+|A))?x)|%%|b[bnx]|[ \nnpqAPMo])*x
                      (?# this regexp can't use [^...] style,
                        # because _preparepats forcibly adds "\n" into [^...],
                        # even though this regexp wants match it against "\n")''',
                  "missing _() in ui message (use () to hide false-positives)"),
               ],
               # warnings
               [
                 # rules depending on implementation of repquote()
                 (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
               ]
             ]
             pyfilters = [
                 (r"""(?msx)(?P<comment>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""", reppython),
             ]
             txtfilters = []
             txtpats = [
               [
                 ('\s$', 'trailing whitespace'),
                 ('.. note::[ \n][^\n]', 'add two newlines after note::')
               ],
               []
             ]
             cpats = [
               [
                 (r'//', "don't use //-style comments"),
                 (r'^  ', "don't use spaces to indent"),
                 (r'\S\t', "don't use tabs except for indent"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
                 (r'.{81}', "line too long"),
                 (r'(while|if|do|for)\(', "use space after while/if/do/for"),
                 (r'return\(', "return is not a function"),
                 (r' ;', "no space before ;"),
                 (r'[^;] \)', "no space before )"),
                 (r'[)][{]', "space between ) and {"),
                 (r'\w+\* \w+', "use int *foo, not int* foo"),
                 (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
                 (r'\w+ (\+\+|--)', "use foo++, not foo ++"),
                 (r'\w,\w', "missing whitespace after ,"),
                 (r'^[^#]\w[+/*]\w', "missing whitespace in expression"),
                 (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'^#\s+\w', "use #foo, not # foo"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'^\s*#import\b', "use only #include in standard C code"),
                 (r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),
                 (r'strcat\(', "don't use strcat"),
                 # rules depending on implementation of repquote()
               ],
               # warnings
               [
                 # rules depending on implementation of repquote()
               ]
             ]
             cfilters = [
                 (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
                 (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
                 (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
                 (r'(\()([^)]+\))', repcallspaces),
             ]
             inutilpats = [
               [
                 (r'\bui\.', "don't use ui in util"),
               ],
               # warnings
               []
             ]
             inrevlogpats = [
               [
                 (r'\brepo\.', "don't use repo in revlog"),
               ],
               # warnings
               []
             ]
             webtemplatefilters = []
             webtemplatepats = [
               [],
               [
                 (r'{desc(\|(?!websub|firstline)[^\|]*)+}',
                  'follow desc keyword with either firstline or websub'),
               ]
             ]
             allfilesfilters = []
             allfilespats = [
               [
                 (r'(http|https)://[a-zA-Z0-9./]*selenic.com/',
                  'use mercurial-scm.org domain URL'),
               ],
               # warnings
               [],
             ]
             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$', '', txtfilters, txtpats),
                 ('web template', r'mercurial/templates/.*\.tmpl', '',
                  webtemplatefilters, webtemplatepats),
                 ('all except for .po', r'.*(?<!\.po)$', '',
                  allfilesfilters, allfilespats),
             ]
             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]
             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:
                     post = pre # discard filtering result of previous check
                     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
             def 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
                 _preparepats()
                 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
                 return ret
             if __name__ == "__main__":
                 sys.exit(main())