upstream/mercurial-mirror Commit - r29330:12c97985

1

#!/usr/bin/env python

1

#!/usr/bin/env python

2

#

2

#

3

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

3

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

4

#

4

#

5

6

#

6

#

7

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

7

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

8

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

8

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

9

10

"""style and portability checker for Mercurial

10

"""style and portability checker for Mercurial

11

12

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

12

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

13

* do the work-around the rule suggests

13

* do the work-around the rule suggests

14

* doublecheck that it is a false match

14

* doublecheck that it is a false match

15

* improve the rule pattern

15

* improve the rule pattern

16

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

16

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

17

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

17

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

18

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

18

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

19

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

19

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

20

"""

20

"""

21

22

from __future__ import absolute_import, print_function

22

from __future__ import absolute_import, print_function

23

import glob

23

import glob

24

import keyword

24

import keyword

25

import optparse

25

import optparse

26

import os

26

import os

27

import re

27

import re

28

import sys

28

import sys

29

if sys.version_info[0] < 3:

29

if sys.version_info[0] < 3:

30

opentext = open

30

opentext = open

31

else:

31

else:

32

def opentext(f):

32

def opentext(f):

33

return open(f, encoding='ascii')

33

return open(f, encoding='ascii')

34

try:

34

try:

35

xrange

35

xrange

36

except NameError:

36

except NameError:

37

xrange = range

37

xrange = range

38

try:

38

try:

39

import re2

39

import re2

40

except ImportError:

40

except ImportError:

41

re2 = None

41

re2 = None

42

43

def compilere(pat, multiline=False):

43

def compilere(pat, multiline=False):

44

if multiline:

44

if multiline:

45

pat = '(?m)' + pat

45

pat = '(?m)' + pat

46

if re2:

46

if re2:

47

try:

47

try:

48

return re2.compile(pat)

48

return re2.compile(pat)

49

except re2.error:

49

except re2.error:

50

pass

50

pass

51

return re.compile(pat)

51

return re.compile(pat)

52

53

def repquote(m):

53

def repquote(m):

54

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

54

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

55

# patterns (especially pypats), before changing this function

55

# patterns (especially pypats), before changing this function

56

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

56

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

57

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

57

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

58

def encodechr(i):

58

def encodechr(i):

59

if i > 255:

59

if i > 255:

60

return 'u'

60

return 'u'

61

c = chr(i)

61

c = chr(i)

62

if c in fixedmap:

62

if c in fixedmap:

63

return fixedmap[c]

63

return fixedmap[c]

64

if c.isalpha():

64

if c.isalpha():

65

return 'x'

65

return 'x'

66

if c.isdigit():

66

if c.isdigit():

67

return 'n'

67

return 'n'

68

return 'o'

68

return 'o'

69

t = m.group('text')

69

t = m.group('text')

70

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

70

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

71

t = t.translate(tt)

71

t = t.translate(tt)

72

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

72

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

73

74

def reppython(m):

74

def reppython(m):

75

comment = m.group('comment')

75

comment = m.group('comment')

76

if comment:

76

if comment:

77

l = len(comment.rstrip())

77

l = len(comment.rstrip())

78

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

78

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

79

return repquote(m)

79

return repquote(m)

80

81

def repcomment(m):

81

def repcomment(m):

82

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

82

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

83

84

def repccomment(m):

84

def repccomment(m):

85

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

85

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

86

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

86

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

87

88

def repcallspaces(m):

88

def repcallspaces(m):

89

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

89

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

90

return m.group(1) + t

90

return m.group(1) + t

91

92

def repinclude(m):

92

def repinclude(m):

93

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

93

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

94

95

def rephere(m):

95

def rephere(m):

96

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

96

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

97

return m.group(1) + t

97

return m.group(1) + t

98

99

100

testpats = [

100

testpats = [

101

[

101

[

102

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

102

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

103

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

103

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

104

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

104

(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"),

105

(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"),

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

(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>'"),

111

(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"),

112

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

113

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

113

(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"),

114

(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"),

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

"use egrep for extended grep syntax"),

119

"use egrep for extended grep syntax"),

120

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

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

(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"),

133

(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"),

134

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

135

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

135

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

136

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

136

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

137

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

137

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

138

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

138

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

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

(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'")

144

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

145

],

145

],

146

# warnings

146

# warnings

147

[

147

[

148

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

148

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

149

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

149

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

150

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

150

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

151

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

151

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

152

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

152

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

153

]

153

]

154

]

154

]

155

156

testfilters = [

156

testfilters = [

157

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

157

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

158

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

158

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

159

]

159

]

160

161

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

161

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

162

uprefix = r"^ \$ "

162

uprefix = r"^ \$ "

163

utestpats = [

163

utestpats = [

164

[

164

[

165

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

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

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

170

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

171

"explicit exit code checks unnecessary"),

171

"explicit exit code checks unnecessary"),

172

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

172

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

173

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

173

(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 "

174

(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

175

"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

176

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

177

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

177

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

178

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

178

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

179

winglobmsg),

179

winglobmsg),

180

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

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

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

197

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

198

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

198

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

199

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

199

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

200

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

200

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

201

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

201

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

202

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

202

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

203

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

203

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

204

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

204

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

205

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

205

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

206

],

206

],

207

# warnings

207

# warnings

208

[

208

[

209

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

209

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

210

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

210

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

211

]

211

]

212

]

212

]

213

214

for i in [0, 1]:

214

for i in [0, 1]:

215

for tp in testpats[i]:

215

for tp in testpats[i]:

216

p = tp[0]

216

p = tp[0]

217

m = tp[1]

217

m = tp[1]

218

if p.startswith(r'^'):

218

if p.startswith(r'^'):

219

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

219

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

220

else:

220

else:

221

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

221

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

222

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

222

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

223

224

utestfilters = [

224

utestfilters = [

225

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

225

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

226

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

226

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

227

]

227

]

228

229

pypats = [

229

pypats = [

230

[

230

[

231

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

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

'dict-from-generator'),

238

'dict-from-generator'),

239

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

239

(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 !='),

240

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

241

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

241

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

242

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

242

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

243

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

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

245

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

246

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

246

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

247

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

247

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

248

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

248

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

249

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

249

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

250

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

250

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

251

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

251

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

252

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

252

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

253

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

253

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

254

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

254

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

255

"don't use camelcase in identifiers"),

255

"don't use camelcase in identifiers"),

256

256

257

"linebreak after :"),

257

"linebreak after :"),

258

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

258

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

259

r'#.*old-style'),

259

r'#.*old-style'),

260

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

260

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

261

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

261

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

262

r'#.*old-style'),

262

r'#.*old-style'),

263

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

263

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

264

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

264

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

265

"Python keyword is not a function"),

265

"Python keyword is not a function"),

266

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

266

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

267

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

267

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

268

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

268

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

269

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

269

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

270

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

270

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

271

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

271

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

272

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

272

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

273

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

273

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

274

"gratuitous whitespace after Python keyword"),

274

"gratuitous whitespace after Python keyword"),

275

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

275

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

276

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

276

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

277

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

277

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

278

"missing whitespace around operator"),

278

"missing whitespace around operator"),

279

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

279

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

280

"missing whitespace around operator"),

280

"missing whitespace around operator"),

281

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

281

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

282

"missing whitespace around operator"),

282

"missing whitespace around operator"),

283

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

283

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

284

"wrong whitespace around ="),

284

"wrong whitespace around ="),

285

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

285

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

286

"no whitespace around = for named parameters"),

286

"no whitespace around = for named parameters"),

287

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

287

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

288

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

288

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

289

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

289

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

290

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

290

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

291

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

291

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

292

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

292

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

293

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

293

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

294

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

294

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

295

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

295

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

296

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

296

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

297

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

297

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

298

"use opener.read() instead"),

298

"use opener.read() instead"),

299

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

299

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

300

"use opener.write() instead"),

300

"use opener.write() instead"),

301

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

301

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

302

"use util.readfile() instead"),

302

"use util.readfile() instead"),

303

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

303

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

304

"use util.writefile() instead"),

304

"use util.writefile() instead"),

305

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

305

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

306

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

306

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

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

319

"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"'),

320

(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

321

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

322

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

322

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

323

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

323

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

324

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

324

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

325

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

325

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

326

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

326

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

327

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

327

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

328

329

# rules depending on implementation of repquote()

329

# rules depending on implementation of repquote()

330

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

330

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

331

'string join across lines with no space'),

331

'string join across lines with no space'),

332

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

332

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

333

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

333

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

334

],

334

],

335

# warnings

335

# warnings

336

[

336

[

337

# rules depending on implementation of repquote()

337

# rules depending on implementation of repquote()

338

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

338

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

339

]

339

]

340

]

340

]

341

342

pyfilters = [

342

pyfilters = [

343

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

343

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

344

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

344

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

345

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

345

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

346

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

346

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

347

]

347

]

348

349

txtfilters = []

349

txtfilters = []

350

351

txtpats = [

351

txtpats = [

352

[

352

[

353

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

353

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

354

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

354

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

355

],

355

],

356

[]

356

[]

357

]

357

]

358

359

cpats = [

359

cpats = [

360

[

360

[

361

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

361

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

362

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

362

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

363

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

363

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

364

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

364

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

365

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

365

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

366

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

366

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

367

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

367

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

368

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

368

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

369

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

369

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

370

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

370

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

371

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

371

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

372

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

372

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

373

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

373

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

374

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

374

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

375

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

375

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

376

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

376

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

377

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

377

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

378

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

378

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

379

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

379

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

380

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

380

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

381

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

381

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

382

383

# rules depending on implementation of repquote()

383

# rules depending on implementation of repquote()

384

],

384

],

385

# warnings

385

# warnings

386

[

386

[

387

# rules depending on implementation of repquote()

387

# rules depending on implementation of repquote()

388

]

388

]

389

]

389

]

390

391

cfilters = [

391

cfilters = [

392

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

392

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

393

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

393

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

394

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

394

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

395

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

395

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

396

]

396

]

397

398

inutilpats = [

398

inutilpats = [

399

[

399

[

400

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

400

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

401

],

401

],

402

# warnings

402

# warnings

403

[]

403

[]

404

]

404

]

405

406

inrevlogpats = [

406

inrevlogpats = [

407

[

407

[

408

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

408

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

409

],

409

],

410

# warnings

410

# warnings

411

[]

411

[]

412

]

412

]

413

414

webtemplatefilters = []

414

webtemplatefilters = []

415

416

webtemplatepats = [

416

webtemplatepats = [

417

[],

417

[],

418

[

418

[

419

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

419

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

420

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

420

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

421

]

421

]

422

]

422

]

423

424

checks = [

424

checks = [

425

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

425

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

426

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

426

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

427

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

427

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

428

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

428

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

429

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

429

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

430

pyfilters, inrevlogpats),

430

pyfilters, inrevlogpats),

431

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

431

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

432

inutilpats),

432

inutilpats),

433

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

433

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

434

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

434

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

435

webtemplatefilters, webtemplatepats),

435

webtemplatefilters, webtemplatepats),

436

]

436

]

437

438

def _preparepats():

438

def _preparepats():

439

for c in checks:

439

for c in checks:

440

failandwarn = c[-1]

440

failandwarn = c[-1]

441

for pats in failandwarn:

441

for pats in failandwarn:

442

for i, pseq in enumerate(pats):

442

for i, pseq in enumerate(pats):

443

# fix-up regexes for multi-line searches

443

# fix-up regexes for multi-line searches

444

p = pseq[0]

444

p = pseq[0]

445

# \s doesn't match \n

445

# \s doesn't match \n

446

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

446

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

447

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

447

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

448

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

448

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

449

450

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

450

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

451

filters = c[3]

451

filters = c[3]

452

for i, flt in enumerate(filters):

452

for i, flt in enumerate(filters):

453

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

453

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

454

_preparepats()

454

_preparepats()

455

456

class norepeatlogger(object):

456

class norepeatlogger(object):

457

def __init__(self):

457

def __init__(self):

458

self._lastseen = None

458

self._lastseen = None

459

460

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

460

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

461

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

461

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

462

463

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

463

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

464

of multiple errors.

464

of multiple errors.

465

466

:fname: filename

466

:fname: filename

467

:lineno: line number

467

:lineno: line number

468

:line: actual content of the line

468

:line: actual content of the line

469

:msg: error message

469

:msg: error message

470

"""

470

"""

471

msgid = fname, lineno, line

471

msgid = fname, lineno, line

472

if msgid != self._lastseen:

472

if msgid != self._lastseen:

473

if blame:

473

if blame:

474

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

474

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

475

else:

475

else:

476

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

476

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

477

print(" > %s" % line)

477

print(" > %s" % line)

478

self._lastseen = msgid

478

self._lastseen = msgid

479

print(" " + msg)

479

print(" " + msg)

480

481

_defaultlogger = norepeatlogger()

481

_defaultlogger = norepeatlogger()

482

483

def getblame(f):

483

def getblame(f):

484

lines = []

484

lines = []

485

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

485

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

486

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

486

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

487

user, rev = start.split()

487

user, rev = start.split()

488

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

488

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

489

return lines

489

return lines

490

491

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

491

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

492

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

492

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

493

"""checks style and portability of a given file

493

"""checks style and portability of a given file

494

495

:f: filepath

495

:f: filepath

496

:logfunc: function used to report error

496

:logfunc: function used to report error

497

logfunc(filename, linenumber, linecontent, errormessage)

497

logfunc(filename, linenumber, linecontent, errormessage)

498

:maxerr: number of error to display before aborting.

498

:maxerr: number of error to display before aborting.

499

Set to false (default) to report all errors

499

Set to false (default) to report all errors

500

501

return True if no error is found, False otherwise.

501

return True if no error is found, False otherwise.

502

"""

502

"""

503

blamecache = None

503

blamecache = None

504

result = True

504

result = True

505

506

try:

506

try:

507

with opentext(f) as fp:

507

with opentext(f) as fp:

508

try:

508

try:

509

pre = post = fp.read()

509

pre = post = fp.read()

510

except UnicodeDecodeError as e:

510

except UnicodeDecodeError as e:

511

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

511

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

512

return result

512

return result

513

except IOError as e:

513

except IOError as e:

514

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

514

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

515

return result

515

return result

516

517

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

517

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

518

if debug:

518

if debug:

519

print(name, f)

519

print(name, f)

520

fc = 0

520

fc = 0

521

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

521

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

522

if debug:

522

if debug:

523

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

523

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

524

name, match, f))

524

name, match, f))

525

continue

525

continue

526

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

526

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

527

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

527

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

528

# no- check- code

528

# no- check- code

529

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

529

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

530

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

530

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

531

# spelling, we write it with the expected spelling from

531

# spelling, we write it with the expected spelling from

532

# tests/test-check-code.t

532

# tests/test-check-code.t

533

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

533

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

534

return "Skip" # skip checking this file

534

return "Skip" # skip checking this file

535

for p, r in filters:

535

for p, r in filters:

536

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

536

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

537

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

537

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

538

if warnings:

538

if warnings:

539

pats = pats[0] + pats[1]

539

pats = pats[0] + pats[1]

540

else:

540

else:

541

pats = pats[0]

541

pats = pats[0]

542

# print post # uncomment to show filtered version

542

# print post # uncomment to show filtered version

543

544

if debug:

544

if debug:

545

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

545

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

546

547

prelines = None

547

prelines = None

548

errors = []

548

errors = []

549

for i, pat in enumerate(pats):

549

for i, pat in enumerate(pats):

550

if len(pat) == 3:

550

if len(pat) == 3:

551

p, msg, ignore = pat

551

p, msg, ignore = pat

552

else:

552

else:

553

p, msg = pat

553

p, msg = pat

554

ignore = None

554

ignore = None

555

if i >= nerrs:

555

if i >= nerrs:

556

msg = "warning: " + msg

556

msg = "warning: " + msg

557

558

pos = 0

558

pos = 0

559

n = 0

559

n = 0

560

for m in p.finditer(post):

560

for m in p.finditer(post):

561

if prelines is None:

561

if prelines is None:

562

prelines = pre.splitlines()

562

prelines = pre.splitlines()

563

postlines = post.splitlines(True)

563

postlines = post.splitlines(True)

564

565

start = m.start()

565

start = m.start()

566

while n < len(postlines):

566

while n < len(postlines):

567

step = len(postlines[n])

567

step = len(postlines[n])

568

if pos + step > start:

568

if pos + step > start:

569

break

569

break

570

pos += step

570

pos += step

571

n += 1

571

n += 1

572

l = prelines[n]

572

l = prelines[n]

573

574

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

574

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

575

if debug:

575

if debug:

576

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

576

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

577

name, f, n))

577

name, f, n))

578

continue

578

continue

579

bd = ""

579

bd = ""

580

if blame:

580

if blame:

581

bd = 'working directory'

581

bd = 'working directory'

582

if not blamecache:

582

if not blamecache:

583

blamecache = getblame(f)

583

blamecache = getblame(f)

584

if n < len(blamecache):

584

if n < len(blamecache):

585

bl, bu, br = blamecache[n]

585

bl, bu, br = blamecache[n]

586

if bl == l:

586

if bl == l:

587

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

587

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

588

589

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

589

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

590

result = False

590

result = False

591

592

errors.sort()

592

errors.sort()

593

for e in errors:

593

for e in errors:

594

logfunc(*e)

594

logfunc(*e)

595

fc += 1

595

fc += 1

596

if maxerr and fc >= maxerr:

596

if maxerr and fc >= maxerr:

597

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

597

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

598

break

598

break

599

600

return result

600

return result

601

602

if __name__ == "__main__":

602

if __name__ == "__main__":

603

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

603

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

604

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

604

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

605

help="include warning-level checks")

605

help="include warning-level checks")

606

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

606

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

607

help="max warnings per file")

607

help="max warnings per file")

608

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

608

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

609

help="use annotate to generate blame info")

609

help="use annotate to generate blame info")

610

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

610

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

611

help="show debug information")

611

help="show debug information")

612

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

612

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

613

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

613

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

614

615

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

615

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

616

lineno=True)

616

lineno=True)

617

(options, args) = parser.parse_args()

617

(options, args) = parser.parse_args()

618

619

if len(args) == 0:

619

if len(args) == 0:

620

check = glob.glob("*")

620

check = glob.glob("*")

621

else:

621

else:

622

check = args

622

check = args

623

624

ret = 0

624

ret = 0

625

for f in check:

625

for f in check:

626

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

626

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

627

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

627

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

628

lineno=options.lineno):

628

lineno=options.lineno):

629

ret = 1

629

ret = 1

630

sys.exit(ret)

630

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
                 fixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
                             '%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}
                 def encodechr(i):
                     if i > 255:
                         return 'u'
                     c = chr(i)
                     if c in fixedmap:
                         return fixedmap[c]
                     if c.isalpha():
                         return 'x'
                     if c.isdigit():
                         return 'n'
                     return 'o'
                 t = m.group('text')
                 tt = ''.join(encodechr(i) for i in xrange(256))
                 t = t.translate(tt)
                 return m.group('quote') + t + m.group('quote')
             def reppython(m):
                 comment = m.group('comment')
                 if comment:
                     l = len(comment.rstrip())
                     return "#" * l + comment[l:]
                 return repquote(m)
             def repcomment(m):
                 return m.group(1) + "#" * len(m.group(2))
             def repccomment(m):
                 t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
                 return m.group(1) + t + "*/"
             def repcallspaces(m):
                 t = re.sub(r"\n\s+", "\n", m.group(2))
                 return m.group(1) + t
             def repinclude(m):
                 return m.group(1) + "<foo>"
             def rephere(m):
                 t = re.sub(r"\S", "x", m.group(2))
                 return m.group(1) + t
             testpats = [
               [
                 (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),
                 (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
                 (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
                 (r'(?<!hg )grep.* -a', "don't use 'grep -a', use in-line python"),
                 (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
                 (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
                 (r'echo -n', "don't use 'echo -n', use printf"),
                 (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
                 (r'head -c', "don't use 'head -c', use 'dd'"),
                 (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
                 (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
                 (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
                 (r'printf.*[^\\]\\([1-9]|0\d)', r"don't use 'printf \NNN', use Python"),
                 (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
                 (r'\$\(.*\)', "don't use $(expr), use `expr`"),
                 (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
                 (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                  "use egrep for extended grep syntax"),
                 (r'/bin/', "don't use explicit paths for tools"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'export .*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
-                (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
+                (r'\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'ui\.(status|progress|write|note|warn)\([\'\"]x',
                  "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)