upstream/mercurial-mirror Commit - r29398:2a54cf92

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):

54

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

53

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

55

# patterns (especially pypats), before changing ~~this function~~

54

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

56

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

55

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

57

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

56

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

58

def encodechr(i):

57

def _repquoteencodechr(i):

59

if i > 255:

58

if i > 255:

60

return 'u'

59

return 'u'

61

c = chr(i)

60

c = chr(i)

62

if c in fixedmap:

61

if c in _repquotefixedmap:

63

return fixedmap[c]

62

return _repquotefixedmap[c]

64

if c.isalpha():

63

if c.isalpha():

65

return 'x'

64

return 'x'

66

if c.isdigit():

65

if c.isdigit():

67

return 'n'

66

return 'n'

68

return 'o'

67

return 'o'

68

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

69

70

def repquote(m):

69

t = m.group('text')

71

t = m.group('text')

70

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

72

t = t.translate(_repquotett)

71

t = t.translate(tt)

72

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

73

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

73

74

def reppython(m):

75

def reppython(m):

75

comment = m.group('comment')

76

comment = m.group('comment')

76

if comment:

77

if comment:

77

l = len(comment.rstrip())

78

l = len(comment.rstrip())

78

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

79

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

79

return repquote(m)

80

return repquote(m)

80

81

def repcomment(m):

82

def repcomment(m):

82

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

83

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

83

84

def repccomment(m):

85

def repccomment(m):

85

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

86

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

86

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

87

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

87

88

def repcallspaces(m):

89

def repcallspaces(m):

89

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

90

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

90

return m.group(1) + t

91

return m.group(1) + t

91

92

def repinclude(m):

93

def repinclude(m):

93

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

94

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

94

95

def rephere(m):

96

def rephere(m):

96

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

97

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

97

return m.group(1) + t

98

return m.group(1) + t

98

99

100

testpats = [

101

testpats = [

101

[

102

[

102

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

103

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

103

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

104

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

104

(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"),

105

(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"),

106

(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"),

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

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

111

(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>'"),

112

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

113

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

113

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

114

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

114

(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"),

115

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

116

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

116

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

117

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

117

(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"),

118

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

119

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

119

"use egrep for extended grep syntax"),

120

"use egrep for extended grep syntax"),

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

(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"),

125

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

126

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

126

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

127

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

127

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

128

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

128

(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'"),

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

(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"),

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

(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"),

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

(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"),

144

(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'")

145

],

146

],

146

# warnings

147

# warnings

147

[

148

[

148

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

149

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

149

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

150

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

150

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

151

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

151

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

152

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

152

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

153

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

153

]

154

]

154

]

155

]

155

156

testfilters = [

157

testfilters = [

157

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

158

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

158

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

159

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

159

]

160

]

160

161

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

162

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

162

uprefix = r"^ \$ "

163

uprefix = r"^ \$ "

163

utestpats = [

164

utestpats = [

164

[

165

[

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

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

171

"explicit exit code checks unnecessary"),

172

"explicit exit code checks unnecessary"),

172

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

173

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

173

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

174

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

174

(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 "

175

"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

176

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

177

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

177

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

178

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

178

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

179

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

179

winglobmsg),

180

winglobmsg),

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

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

206

],

207

],

207

# warnings

208

# warnings

208

[

209

[

209

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

210

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

210

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

211

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

211

]

212

]

212

]

213

]

213

214

for i in [0, 1]:

215

for i in [0, 1]:

215

for tp in testpats[i]:

216

for tp in testpats[i]:

216

p = tp[0]

217

p = tp[0]

217

m = tp[1]

218

m = tp[1]

218

if p.startswith(r'^'):

219

if p.startswith(r'^'):

219

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

220

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

220

else:

221

else:

221

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

222

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

222

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

223

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

223

224

utestfilters = [

225

utestfilters = [

225

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

226

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

226

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

227

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

227

]

228

]

228

229

pypats = [

230

pypats = [

230

[

231

[

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

(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 {}',

238

'dict-from-generator'),

239

'dict-from-generator'),

239

(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+"),

240

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

241

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

241

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

242

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

242

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

243

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

243

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

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

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

255

"don't use camelcase in identifiers"),

256

"don't use camelcase in identifiers"),

256

257

257

"linebreak after :"),

258

"linebreak after :"),

258

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

259

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

259

r'#.*old-style'),

260

r'#.*old-style'),

260

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

261

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

261

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

262

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

262

r'#.*old-style'),

263

r'#.*old-style'),

263

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

264

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

264

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

265

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

265

"Python keyword is not a function"),

266

"Python keyword is not a function"),

266

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

267

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

267

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

268

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

268

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

269

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

269

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

270

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

270

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

271

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

271

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

272

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

272

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

273

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

273

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

274

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

274

"gratuitous whitespace after Python keyword"),

275

"gratuitous whitespace after Python keyword"),

275

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

276

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

276

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

277

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

277

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

278

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

278

"missing whitespace around operator"),

279

"missing whitespace around operator"),

279

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

280

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

280

"missing whitespace around operator"),

281

"missing whitespace around operator"),

281

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

282

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

282

"missing whitespace around operator"),

283

"missing whitespace around operator"),

283

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

284

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

284

"wrong whitespace around ="),

285

"wrong whitespace around ="),

285

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

286

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

286

"no whitespace around = for named parameters"),

287

"no whitespace around = for named parameters"),

287

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

288

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

288

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

289

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

289

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

290

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

290

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

291

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

291

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

292

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

292

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

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

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

298

"use opener.read() instead"),

299

"use opener.read() instead"),

299

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

300

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

300

"use opener.write() instead"),

301

"use opener.write() instead"),

301

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

302

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

302

"use util.readfile() instead"),

303

"use util.readfile() instead"),

303

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

304

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

304

"use util.writefile() instead"),

305

"use util.writefile() instead"),

305

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

306

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

306

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

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

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

320

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

320

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

321

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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

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

328

329

# rules depending on implementation of repquote()

330

# rules depending on implementation of repquote()

330

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

331

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

331

'string join across lines with no space'),

332

'string join across lines with no space'),

332

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

333

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

333

[ \t\n#]*

334

[ \t\n#]*

334

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

335

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

335

# contains translatable message)

336

# contains translatable message)

336

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

337

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

337

(?# sequence consisting of below might precede translatable message

338

(?# sequence consisting of below might precede translatable message

338

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

339

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

339

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

340

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

340

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

341

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

341

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

342

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

342

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

343

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

343

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

344

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

344

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

345

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

345

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

346

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

346

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

347

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

347

],

348

],

348

# warnings

349

# warnings

349

[

350

[

350

# rules depending on implementation of repquote()

351

# rules depending on implementation of repquote()

351

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

352

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

352

]

353

]

353

]

354

]

354

355

pyfilters = [

356

pyfilters = [

356

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

357

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

357

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

358

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

358

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

359

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

359

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

360

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

360

]

361

]

361

362

txtfilters = []

363

txtfilters = []

363

364

txtpats = [

365

txtpats = [

365

[

366

[

366

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

367

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

367

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

368

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

368

],

369

],

369

[]

370

[]

370

]

371

]

371

372

cpats = [

373

cpats = [

373

[

374

[

374

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

375

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

375

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

376

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

376

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

377

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

377

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

378

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

378

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

379

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

379

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

380

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

380

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

381

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

381

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

382

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

382

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

383

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

383

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

384

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

384

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

385

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

385

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

386

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

386

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

387

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

387

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

388

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

388

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

389

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

389

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

390

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

390

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

391

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

391

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

392

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

392

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

393

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

393

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

394

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

394

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

395

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

395

396

# rules depending on implementation of repquote()

397

# rules depending on implementation of repquote()

397

],

398

],

398

# warnings

399

# warnings

399

[

400

[

400

# rules depending on implementation of repquote()

401

# rules depending on implementation of repquote()

401

]

402

]

402

]

403

]

403

404

cfilters = [

405

cfilters = [

405

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

406

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

406

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

407

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

407

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

408

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

408

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

409

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

409

]

410

]

410

411

inutilpats = [

412

inutilpats = [

412

[

413

[

413

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

414

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

414

],

415

],

415

# warnings

416

# warnings

416

[]

417

[]

417

]

418

]

418

419

inrevlogpats = [

420

inrevlogpats = [

420

[

421

[

421

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

422

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

422

],

423

],

423

# warnings

424

# warnings

424

[]

425

[]

425

]

426

]

426

427

webtemplatefilters = []

428

webtemplatefilters = []

428

429

webtemplatepats = [

430

webtemplatepats = [

430

[],

431

[],

431

[

432

[

432

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

433

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

433

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

434

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

434

]

435

]

435

]

436

]

436

437

checks = [

438

checks = [

438

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

439

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

439

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

440

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

440

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

441

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

441

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

442

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

442

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

443

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

443

pyfilters, inrevlogpats),

444

pyfilters, inrevlogpats),

444

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

445

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

445

inutilpats),

446

inutilpats),

446

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

447

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

447

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

448

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

448

webtemplatefilters, webtemplatepats),

449

webtemplatefilters, webtemplatepats),

449

]

450

]

450

451

def _preparepats():

452

def _preparepats():

452

for c in checks:

453

for c in checks:

453

failandwarn = c[-1]

454

failandwarn = c[-1]

454

for pats in failandwarn:

455

for pats in failandwarn:

455

for i, pseq in enumerate(pats):

456

for i, pseq in enumerate(pats):

456

# fix-up regexes for multi-line searches

457

# fix-up regexes for multi-line searches

457

p = pseq[0]

458

p = pseq[0]

458

# \s doesn't match \n

459

# \s doesn't match \n

459

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

460

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

460

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

461

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

461

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

462

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

462

463

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

464

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

464

filters = c[3]

465

filters = c[3]

465

for i, flt in enumerate(filters):

466

for i, flt in enumerate(filters):

466

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

467

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

467

_preparepats()

468

_preparepats()

468

469

class norepeatlogger(object):

470

class norepeatlogger(object):

470

def __init__(self):

471

def __init__(self):

471

self._lastseen = None

472

self._lastseen = None

472

473

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

474

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

474

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

475

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

475

476

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

477

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

477

of multiple errors.

478

of multiple errors.

478

479

:fname: filename

480

:fname: filename

480

:lineno: line number

481

:lineno: line number

481

:line: actual content of the line

482

:line: actual content of the line

482

:msg: error message

483

:msg: error message

483

"""

484

"""

484

msgid = fname, lineno, line

485

msgid = fname, lineno, line

485

if msgid != self._lastseen:

486

if msgid != self._lastseen:

486

if blame:

487

if blame:

487

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

488

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

488

else:

489

else:

489

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

490

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

490

print(" > %s" % line)

491

print(" > %s" % line)

491

self._lastseen = msgid

492

self._lastseen = msgid

492

print(" " + msg)

493

print(" " + msg)

493

494

_defaultlogger = norepeatlogger()

495

_defaultlogger = norepeatlogger()

495

496

def getblame(f):

497

def getblame(f):

497

lines = []

498

lines = []

498

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

499

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

499

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

500

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

500

user, rev = start.split()

501

user, rev = start.split()

501

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

502

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

502

return lines

503

return lines

503

504

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

505

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

505

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

506

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

506

"""checks style and portability of a given file

507

"""checks style and portability of a given file

507

508

:f: filepath

509

:f: filepath

509

:logfunc: function used to report error

510

:logfunc: function used to report error

510

logfunc(filename, linenumber, linecontent, errormessage)

511

logfunc(filename, linenumber, linecontent, errormessage)

511

:maxerr: number of error to display before aborting.

512

:maxerr: number of error to display before aborting.

512

Set to false (default) to report all errors

513

Set to false (default) to report all errors

513

514

return True if no error is found, False otherwise.

515

return True if no error is found, False otherwise.

515

"""

516

"""

516

blamecache = None

517

blamecache = None

517

result = True

518

result = True

518

519

try:

520

try:

520

with opentext(f) as fp:

521

with opentext(f) as fp:

521

try:

522

try:

522

pre = post = fp.read()

523

pre = post = fp.read()

523

except UnicodeDecodeError as e:

524

except UnicodeDecodeError as e:

524

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

525

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

525

return result

526

return result

526

except IOError as e:

527

except IOError as e:

527

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

528

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

528

return result

529

return result

529

530

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

531

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

531

if debug:

532

if debug:

532

print(name, f)

533

print(name, f)

533

fc = 0

534

fc = 0

534

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

535

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

535

if debug:

536

if debug:

536

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

537

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

537

name, match, f))

538

name, match, f))

538

continue

539

continue

539

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

540

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

540

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

541

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

541

# no- check- code

542

# no- check- code

542

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

543

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

543

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

544

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

544

# spelling, we write it with the expected spelling from

545

# spelling, we write it with the expected spelling from

545

# tests/test-check-code.t

546

# tests/test-check-code.t

546

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

547

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

547

return "Skip" # skip checking this file

548

return "Skip" # skip checking this file

548

for p, r in filters:

549

for p, r in filters:

549

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

550

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

550

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

551

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

551

if warnings:

552

if warnings:

552

pats = pats[0] + pats[1]

553

pats = pats[0] + pats[1]

553

else:

554

else:

554

pats = pats[0]

555

pats = pats[0]

555

# print post # uncomment to show filtered version

556

# print post # uncomment to show filtered version

556

557

if debug:

558

if debug:

558

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

559

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

559

560

prelines = None

561

prelines = None

561

errors = []

562

errors = []

562

for i, pat in enumerate(pats):

563

for i, pat in enumerate(pats):

563

if len(pat) == 3:

564

if len(pat) == 3:

564

p, msg, ignore = pat

565

p, msg, ignore = pat

565

else:

566

else:

566

p, msg = pat

567

p, msg = pat

567

ignore = None

568

ignore = None

568

if i >= nerrs:

569

if i >= nerrs:

569

msg = "warning: " + msg

570

msg = "warning: " + msg

570

571

pos = 0

572

pos = 0

572

n = 0

573

n = 0

573

for m in p.finditer(post):

574

for m in p.finditer(post):

574

if prelines is None:

575

if prelines is None:

575

prelines = pre.splitlines()

576

prelines = pre.splitlines()

576

postlines = post.splitlines(True)

577

postlines = post.splitlines(True)

577

578

start = m.start()

579

start = m.start()

579

while n < len(postlines):

580

while n < len(postlines):

580

step = len(postlines[n])

581

step = len(postlines[n])

581

if pos + step > start:

582

if pos + step > start:

582

break

583

break

583

pos += step

584

pos += step

584

n += 1

585

n += 1

585

l = prelines[n]

586

l = prelines[n]

586

587

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

588

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

588

if debug:

589

if debug:

589

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

590

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

590

name, f, n))

591

name, f, n))

591

continue

592

continue

592

bd = ""

593

bd = ""

593

if blame:

594

if blame:

594

bd = 'working directory'

595

bd = 'working directory'

595

if not blamecache:

596

if not blamecache:

596

blamecache = getblame(f)

597

blamecache = getblame(f)

597

if n < len(blamecache):

598

if n < len(blamecache):

598

bl, bu, br = blamecache[n]

599

bl, bu, br = blamecache[n]

599

if bl == l:

600

if bl == l:

600

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

601

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

601

602

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

603

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

603

result = False

604

result = False

604

605

errors.sort()

606

errors.sort()

606

for e in errors:

607

for e in errors:

607

logfunc(*e)

608

logfunc(*e)

608

fc += 1

609

fc += 1

609

if maxerr and fc >= maxerr:

610

if maxerr and fc >= maxerr:

610

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

611

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

611

break

612

break

612

613

return result

614

return result

614

615

if __name__ == "__main__":

616

if __name__ == "__main__":

616

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

617

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

617

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

618

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

618

help="include warning-level checks")

619

help="include warning-level checks")

619

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

620

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

620

help="max warnings per file")

621

help="max warnings per file")

621

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

622

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

622

help="use annotate to generate blame info")

623

help="use annotate to generate blame info")

623

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

624

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

624

help="show debug information")

625

help="show debug information")

625

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

626

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

626

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

627

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

627

628

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

629

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

629

lineno=True)

630

lineno=True)

630

(options, args) = parser.parse_args()

631

(options, args) = parser.parse_args()

631

632

if len(args) == 0:

633

if len(args) == 0:

633

check = glob.glob("*")

634

check = glob.glob("*")

634

else:

635

else:

635

check = args

636

check = args

636

637

ret = 0

638

ret = 0

638

for f in check:

639

for f in check:

639

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

640

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

640

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

641

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

641

lineno=options.lineno):

642

lineno=options.lineno):

642

ret = 1

643

ret = 1

643

sys.exit(ret)

644

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):
             # check "rules depending on implementation of repquote()" in each
-                # patterns (especially pypats), before changing this function
+            # patterns (especially pypats), before changing around repquote()
-                fixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
+            _repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
                                  '%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}
-                def encodechr(i):
+            def _repquoteencodechr(i):
                 if i > 255:
                     return 'u'
                 c = chr(i)
-                    if c in fixedmap:
+                if c in _repquotefixedmap:
-                        return fixedmap[c]
+                    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')
-                tt = ''.join(encodechr(i) for i in xrange(256))
+                t = t.translate(_repquotett)
-                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'\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'")
               ],
               # 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'[^\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'\.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'),
               ]
             ]
             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)

               $ cat > correct.py <<EOF
               > def toto(arg1, arg2):
               >     del arg2
               >     return (5 + 6, 9)
               > EOF
               $ cat > wrong.py <<EOF
               > def toto( arg1, arg2):
               >     del(arg2)
               >     return ( 5+6, 9)
               > EOF
               $ cat > quote.py <<EOF
               > # let's use quote in comments
               > (''' ( 4x5 )
               > but """\\''' and finally''',
               > """let's fool checkpatch""", '1+2',
               > '"""', 42+1, """and
               > ( 4-1 ) """, "( 1+1 )\" and ")
               > a, '\\\\\\\\', "\\\\\\" x-2", "c-1"
               > EOF
               $ cat > classstyle.py <<EOF
               > class newstyle_class(object):
               >     pass
               >
               > class oldstyle_class:
               >     pass
               >
               > class empty():
               >     pass
               >
               > no_class = 1:
               >     pass
               > EOF
               $ check_code="$TESTDIR"/../contrib/check-code.py
               $ "$check_code" ./wrong.py ./correct.py ./quote.py ./classstyle.py
               ./wrong.py:1:
                > def toto( arg1, arg2):
                gratuitous whitespace in () or []
               ./wrong.py:2:
                >     del(arg2)
                Python keyword is not a function
               ./wrong.py:3:
                >     return ( 5+6, 9)
                gratuitous whitespace in () or []
                missing whitespace in expression
               ./quote.py:5:
                > '"""', 42+1, """and
                missing whitespace in expression
               ./classstyle.py:4:
                > class oldstyle_class:
                old-style class, use class foo(object)
               ./classstyle.py:7:
                > class empty():
                class foo() creates old style object, use class foo(object)
               [1]
               $ cat > python3-compat.py << EOF
               > foo <> bar
               > reduce(lambda a, b: a + b, [1, 2, 3, 4])
               > dict(key=value)
               > EOF
               $ "$check_code" python3-compat.py
               python3-compat.py:1:
                > foo <> bar
                <> operator is not available in Python 3+, use !=
               python3-compat.py:2:
                > reduce(lambda a, b: a + b, [1, 2, 3, 4])
                reduce is not available in Python 3+
               python3-compat.py:3:
                > dict(key=value)
                dict() is different in Py2 and 3 and is slower than {}
               [1]
               $ cat > foo.c <<EOF
               > void narf() {
               > 	strcpy(foo, bar);
               > 	// strcpy_s is okay, but this comment is not
               > 	strcpy_s(foo, bar);
               > }
               > EOF
               $ "$check_code" ./foo.c
               ./foo.c:2:
                > 	strcpy(foo, bar);
                don't use strcpy, use strlcpy or memcpy
               ./foo.c:3:
                > 	// strcpy_s is okay, but this comment is not
                don't use //-style comments
               [1]
               $ cat > is-op.py <<EOF
               > # is-operator comparing number or string literal
               > x = None
               > y = x is 'foo'
               > y = x is "foo"
               > y = x is 5346
               > y = x is -6
               > y = x is not 'foo'
               > y = x is not "foo"
               > y = x is not 5346
               > y = x is not -6
               > EOF
               $ "$check_code" ./is-op.py
               ./is-op.py:3:
                > y = x is 'foo'
                object comparison with literal
               ./is-op.py:4:
                > y = x is "foo"
                object comparison with literal
               ./is-op.py:5:
                > y = x is 5346
                object comparison with literal
               ./is-op.py:6:
                > y = x is -6
                object comparison with literal
               ./is-op.py:7:
                > y = x is not 'foo'
                object comparison with literal
               ./is-op.py:8:
                > y = x is not "foo"
                object comparison with literal
               ./is-op.py:9:
                > y = x is not 5346
                object comparison with literal
               ./is-op.py:10:
                > y = x is not -6
                object comparison with literal
               [1]
               $ cat > for-nolineno.py <<EOF
               > except:
               > EOF
               $ "$check_code" for-nolineno.py --nolineno
               for-nolineno.py:0:
                > except:
                naked except clause
               [1]
               $ cat > warning.t <<EOF
               >   $ function warnonly {
               >   > }
               >   $ diff -N aaa
               >   $ function onwarn {}
               > EOF
               $ "$check_code" warning.t
               $ "$check_code" --warn warning.t
               warning.t:1:
                >   $ function warnonly {
                warning: don't use 'function', use old style
               warning.t:3:
                >   $ diff -N aaa
                warning: don't use 'diff -N'
               warning.t:4:
                >   $ function onwarn {}
                warning: don't use 'function', use old style
               [1]
               $ cat > raise-format.py <<EOF
               > raise SomeException, message
               > # this next line is okay
               > raise SomeException(arg1, arg2)
               > EOF
               $ "$check_code" not-existing.py raise-format.py
               Skipping*not-existing.py* (glob)
               raise-format.py:1:
                > raise SomeException, message
                don't use old-style two-argument raise, use Exception(message)
               [1]
               $ cat > rst.py <<EOF
               > """problematic rst text
               >
               > .. note::
               >     wrong
               > """
               >
               > '''
               >
               > .. note::
               >
               >     valid
               >
               > new text
               >
               >     .. note::
               >
               >         also valid
               > '''
               >
               > """mixed
               >
               > .. note::
               >
               >   good
               >
               >     .. note::
               >         plus bad
               > """
               > EOF
               $ $check_code -w rst.py
               rst.py:3:
                > .. note::
                warning: add two newlines after '.. note::'
               rst.py:26:
                >     .. note::
                warning: add two newlines after '.. note::'
               [1]
               $ cat > ./map-inside-gettext.py <<EOF
               > print _("map inside gettext %s" % v)
               >
               > print _("concatenating " " by " " space %s" % v)
               > print _("concatenating " + " by " + " '+' %s" % v)
               >
               > print _("mapping operation in different line %s"
               >         % v)
               >
               > print _(
               >         "leading spaces inside of '(' %s" % v)
               > EOF
               $ "$check_code" ./map-inside-gettext.py
               ./map-inside-gettext.py:1:
                > print _("map inside gettext %s" % v)
                don't use % inside _()
               ./map-inside-gettext.py:3:
                > print _("concatenating " " by " " space %s" % v)
                don't use % inside _()
               ./map-inside-gettext.py:4:
                > print _("concatenating " + " by " + " '+' %s" % v)
                don't use % inside _()
               ./map-inside-gettext.py:6:
                > print _("mapping operation in different line %s"
                don't use % inside _()
               ./map-inside-gettext.py:9:
                > print _(
                don't use % inside _()
               [1]
             web templates
               $ mkdir -p mercurial/templates
               $ cat > mercurial/templates/example.tmpl <<EOF
               > {desc}
               > {desc|escape}
               > {desc|firstline}
               > {desc|websub}
               > EOF
               $ "$check_code" --warnings mercurial/templates/example.tmpl
               mercurial/templates/example.tmpl:2:
                > {desc|escape}
                warning: follow desc keyword with either firstline or websub
               [1]
             'string join across lines with no space' detection
               $ cat > stringjoin.py <<EOF
               > foo = (' foo'
               >        'bar foo.'
               >        'bar foo:'
               >        'bar foo@'
               >        'bar foo%'
               >        'bar foo*'
               >        'bar foo+'
               >        'bar foo-'
               >        'bar')
               > EOF
             'missing _() in ui message' detection
               $ cat > uigettext.py <<EOF
               > ui.status("% 10s %05d % -3.2f %*s %%"
               >           # this use '\\\\' instead of '\\', because the latter in
               >           # heredoc on shell becomes just '\'
               >           '\\\\ \n \t \0'
               >           """12345
               >           """
               >           '''.:*+-=
               >           ''' "%-6d \n 123456 .:*+-= foobar")
               > EOF
-              $ "$check_code" stringjoin.py
+            (Checking multiple invalid files at once examines whether caching
+            translation table for repquote() works as expected or not. All files
+            should break rules depending on result of repquote(), in this case)
+              $ "$check_code" stringjoin.py uigettext.py
               stringjoin.py:1:
                > foo = (' foo'
                string join across lines with no space
               stringjoin.py:2:
                >        'bar foo.'
                string join across lines with no space
               stringjoin.py:3:
                >        'bar foo:'
                string join across lines with no space
               stringjoin.py:4:
                >        'bar foo@'
                string join across lines with no space
               stringjoin.py:5:
                >        'bar foo%'
                string join across lines with no space
               stringjoin.py:6:
                >        'bar foo*'
                string join across lines with no space
               stringjoin.py:7:
                >        'bar foo+'
                string join across lines with no space
               stringjoin.py:8:
                >        'bar foo-'
                string join across lines with no space
-              [1]
-              $ "$check_code" uigettext.py
               uigettext.py:1:
                > ui.status("% 10s %05d % -3.2f %*s %%"
                missing _() in ui message (use () to hide false-positives)
               [1]