upstream/mercurial-mirror Commit - r28884:75309bad

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

try:

29

try:

30

import re2

30

import re2

31

except ImportError:

31

except ImportError:

32

re2 = None

32

re2 = None

33

34

def compilere(pat, multiline=False):

34

def compilere(pat, multiline=False):

35

if multiline:

35

if multiline:

36

pat = '(?m)' + pat

36

pat = '(?m)' + pat

37

if re2:

37

if re2:

38

try:

38

try:

39

return re2.compile(pat)

39

return re2.compile(pat)

40

except re2.error:

40

except re2.error:

41

pass

41

pass

42

return re.compile(pat)

42

return re.compile(pat)

43

44

def repquote(m):

44

def repquote(m):

45

fromc = '.:'

45

fromc = '.:'

46

tochr = 'pq'

46

tochr = 'pq'

47

def encodechr(i):

47

def encodechr(i):

48

if i > 255:

48

if i > 255:

49

return 'u'

49

return 'u'

50

c = chr(i)

50

c = chr(i)

51

if c in ' \n':

51

if c in ' \n':

52

return c

52

return c

53

if c.isalpha():

53

if c.isalpha():

54

return 'x'

54

return 'x'

55

if c.isdigit():

55

if c.isdigit():

56

return 'n'

56

return 'n'

57

try:

57

try:

58

return tochr[fromc.find(c)]

58

return tochr[fromc.find(c)]

59

except (ValueError, IndexError):

59

except (ValueError, IndexError):

60

return 'o'

60

return 'o'

61

t = m.group('text')

61

t = m.group('text')

62

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

62

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

63

t = t.translate(tt)

63

t = t.translate(tt)

64

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

64

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

65

66

def reppython(m):

66

def reppython(m):

67

comment = m.group('comment')

67

comment = m.group('comment')

68

if comment:

68

if comment:

69

l = len(comment.rstrip())

69

l = len(comment.rstrip())

70

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

70

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

71

return repquote(m)

71

return repquote(m)

72

73

def repcomment(m):

73

def repcomment(m):

74

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

74

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

75

76

def repccomment(m):

76

def repccomment(m):

77

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

77

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

78

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

78

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

79

80

def repcallspaces(m):

80

def repcallspaces(m):

81

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

81

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

82

return m.group(1) + t

82

return m.group(1) + t

83

84

def repinclude(m):

84

def repinclude(m):

85

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

85

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

86

87

def rephere(m):

87

def rephere(m):

88

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

88

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

89

return m.group(1) + t

89

return m.group(1) + t

90

91

92

testpats = [

92

testpats = [

93

[

93

[

94

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

94

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

95

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

95

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

96

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

96

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

97

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

97

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

98

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

98

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

99

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

99

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

100

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

100

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

101

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

101

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

102

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

102

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

103

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

103

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

104

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

104

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

105

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

105

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

106

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

106

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

107

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

107

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

108

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

108

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

109

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

109

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

110

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

110

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

111

"use egrep for extended grep syntax"),

111

"use egrep for extended grep syntax"),

112

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

112

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

113

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

113

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

114

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

114

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

115

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

115

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

116

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

116

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

117

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

117

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

118

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

118

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

119

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

119

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

120

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

120

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

121

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

121

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

122

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

122

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

123

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

123

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

124

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

124

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

125

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

125

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

126

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

126

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

127

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

127

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

128

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

128

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

129

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

129

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

130

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

130

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

131

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

131

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

132

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

132

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

133

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

133

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

134

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

134

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

135

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

135

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

136

],

136

],

137

# warnings

137

# warnings

138

[

138

[

139

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

139

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

140

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

140

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

141

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

141

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

142

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

142

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

143

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

143

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

144

]

144

]

145

]

145

]

146

147

testfilters = [

147

testfilters = [

148

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

148

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

149

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

149

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

150

]

150

]

151

152

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

152

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

153

uprefix = r"^ \$ "

153

uprefix = r"^ \$ "

154

utestpats = [

154

utestpats = [

155

[

155

[

156

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

156

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

157

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

157

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

158

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

158

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

159

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

159

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

160

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

160

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

161

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

161

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

162

"explicit exit code checks unnecessary"),

162

"explicit exit code checks unnecessary"),

163

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

163

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

164

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

164

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

165

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

165

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

166

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

166

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

167

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

167

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

168

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

168

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

169

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

169

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

170

winglobmsg),

170

winglobmsg),

171

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

171

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

172

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

172

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

173

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

173

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

174

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

174

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

175

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

175

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

176

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

176

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

177

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

177

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

178

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

178

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

179

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

179

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

180

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

180

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

181

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

181

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

182

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

182

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

183

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

183

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

184

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

184

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

185

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

185

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

186

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

186

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

187

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

187

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

188

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

188

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

189

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

189

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

190

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

190

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

191

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

191

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

192

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

192

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

193

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

193

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

194

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

194

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

195

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

195

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

196

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

196

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

197

],

197

],

198

# warnings

198

# warnings

199

[

199

[

200

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

200

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

201

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

201

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

202

]

202

]

203

]

203

]

204

205

for i in [0, 1]:

205

for i in [0, 1]:

206

for tp in testpats[i]:

206

for tp in testpats[i]:

207

p = tp[0]

207

p = tp[0]

208

m = tp[1]

208

m = tp[1]

209

if p.startswith(r'^'):

209

if p.startswith(r'^'):

210

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

210

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

211

else:

211

else:

212

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

212

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

213

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

213

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

214

215

utestfilters = [

215

utestfilters = [

216

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

216

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

217

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

217

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

218

]

218

]

219

220

pypats = [

220

pypats = [

221

[

221

[

222

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

222

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

223

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

223

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

224

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

224

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

225

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

225

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

226

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

226

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

227

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

227

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

228

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

228

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

229

'dict-from-generator'),

229

'dict-from-generator'),

230

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

230

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

231

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

231

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

232

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

232

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

233

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

233

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

234

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

234

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

235

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

235

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

236

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

236

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

237

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

237

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

238

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

238

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

239

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

239

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

240

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

240

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

241

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

241

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

242

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

242

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

243

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

243

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

244

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

244

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

245

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

245

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

246

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

246

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

247

"don't use camelcase in identifiers"),

247

"don't use camelcase in identifiers"),

248

248

249

"linebreak after :"),

249

"linebreak after :"),

250

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

250

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

251

r'#.*old-style'),

251

r'#.*old-style'),

252

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

252

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

253

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

253

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

254

r'#.*old-style'),

254

r'#.*old-style'),

255

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

255

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

256

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

256

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

257

"Python keyword is not a function"),

257

"Python keyword is not a function"),

258

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

258

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

259

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

259

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

260

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

260

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

261

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

261

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

262

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

262

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

263

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

263

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

264

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

264

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

265

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

265

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

266

"gratuitous whitespace after Python keyword"),

266

"gratuitous whitespace after Python keyword"),

267

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

267

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

268

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

268

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

269

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

269

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

270

"missing whitespace around operator"),

270

"missing whitespace around operator"),

271

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

271

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

272

"missing whitespace around operator"),

272

"missing whitespace around operator"),

273

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

273

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

274

"missing whitespace around operator"),

274

"missing whitespace around operator"),

275

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

275

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

276

"wrong whitespace around ="),

276

"wrong whitespace around ="),

277

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

277

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

278

"no whitespace around = for named parameters"),

278

"no whitespace around = for named parameters"),

279

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

279

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

280

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

280

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

281

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

281

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

282

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

282

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

283

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

283

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

284

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

284

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

285

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

285

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

286

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

286

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

287

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

287

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

288

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

288

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

289

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

289

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

290

"use opener.read() instead"),

290

"use opener.read() instead"),

291

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

291

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

292

"use opener.write() instead"),

292

"use opener.write() instead"),

293

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

293

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

294

"use util.readfile() instead"),

294

"use util.readfile() instead"),

295

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

295

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

296

"use util.writefile() instead"),

296

"use util.writefile() instead"),

297

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

297

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

298

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

298

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

299

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

299

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

300

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

300

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

301

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

301

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

302

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

302

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

303

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

303

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

304

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

304

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

305

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

305

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

306

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

306

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

307

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

307

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

308

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

308

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

309

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

309

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

310

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

310

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

311

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

311

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

312

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

312

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

313

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

313

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

314

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

314

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

315

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

315

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

316

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

316

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

317

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

317

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

318

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

318

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

319

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

320

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

319

],

321

],

320

# warnings

322

# warnings

321

[

323

[

322

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

324

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

323

]

325

]

324

]

326

]

325

327

326

pyfilters = [

328

pyfilters = [

327

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

329

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

328

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

330

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

329

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

331

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

330

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

332

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

331

]

333

]

332

334

333

txtfilters = []

335

txtfilters = []

334

336

335

txtpats = [

337

txtpats = [

336

[

338

[

337

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

339

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

338

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

340

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

339

],

341

],

340

[]

342

[]

341

]

343

]

342

344

343

cpats = [

345

cpats = [

344

[

346

[

345

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

347

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

346

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

348

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

347

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

349

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

348

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

350

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

349

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

351

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

350

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

352

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

351

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

353

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

352

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

354

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

353

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

355

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

354

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

356

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

355

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

357

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

356

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

358

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

357

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

359

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

358

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

360

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

359

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

361

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

360

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

362

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

361

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

363

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

362

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

364

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

363

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

365

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

364

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

366

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

365

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

367

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

366

],

368

],

367

# warnings

369

# warnings

368

[]

370

[]

369

]

371

]

370

372

371

cfilters = [

373

cfilters = [

372

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

374

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

373

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

375

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

374

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

376

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

375

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

377

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

376

]

378

]

377

379

378

inutilpats = [

380

inutilpats = [

379

[

381

[

380

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

382

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

381

],

383

],

382

# warnings

384

# warnings

383

[]

385

[]

384

]

386

]

385

387

386

inrevlogpats = [

388

inrevlogpats = [

387

[

389

[

388

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

390

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

389

],

391

],

390

# warnings

392

# warnings

391

[]

393

[]

392

]

394

]

393

395

394

webtemplatefilters = []

396

webtemplatefilters = []

395

397

396

webtemplatepats = [

398

webtemplatepats = [

397

[],

399

[],

398

[

400

[

399

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

401

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

400

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

402

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

401

]

403

]

402

]

404

]

403

405

404

checks = [

406

checks = [

405

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

407

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

406

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

408

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

407

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

409

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

408

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

410

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

409

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

411

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

410

pyfilters, inrevlogpats),

412

pyfilters, inrevlogpats),

411

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

413

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

412

inutilpats),

414

inutilpats),

413

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

415

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

414

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

416

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

415

webtemplatefilters, webtemplatepats),

417

webtemplatefilters, webtemplatepats),

416

]

418

]

417

419

418

def _preparepats():

420

def _preparepats():

419

for c in checks:

421

for c in checks:

420

failandwarn = c[-1]

422

failandwarn = c[-1]

421

for pats in failandwarn:

423

for pats in failandwarn:

422

for i, pseq in enumerate(pats):

424

for i, pseq in enumerate(pats):

423

# fix-up regexes for multi-line searches

425

# fix-up regexes for multi-line searches

424

p = pseq[0]

426

p = pseq[0]

425

# \s doesn't match \n

427

# \s doesn't match \n

426

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

428

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

427

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

429

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

428

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

430

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

429

431

430

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

432

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

431

filters = c[3]

433

filters = c[3]

432

for i, flt in enumerate(filters):

434

for i, flt in enumerate(filters):

433

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

435

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

434

_preparepats()

436

_preparepats()

435

437

436

class norepeatlogger(object):

438

class norepeatlogger(object):

437

def __init__(self):

439

def __init__(self):

438

self._lastseen = None

440

self._lastseen = None

439

441

440

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

442

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

441

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

443

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

442

444

443

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

445

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

444

of multiple errors.

446

of multiple errors.

445

447

446

:fname: filename

448

:fname: filename

447

:lineno: line number

449

:lineno: line number

448

:line: actual content of the line

450

:line: actual content of the line

449

:msg: error message

451

:msg: error message

450

"""

452

"""

451

msgid = fname, lineno, line

453

msgid = fname, lineno, line

452

if msgid != self._lastseen:

454

if msgid != self._lastseen:

453

if blame:

455

if blame:

454

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

456

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

455

else:

457

else:

456

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

458

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

457

print(" > %s" % line)

459

print(" > %s" % line)

458

self._lastseen = msgid

460

self._lastseen = msgid

459

print(" " + msg)

461

print(" " + msg)

460

462

461

_defaultlogger = norepeatlogger()

463

_defaultlogger = norepeatlogger()

462

464

463

def getblame(f):

465

def getblame(f):

464

lines = []

466

lines = []

465

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

467

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

466

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

468

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

467

user, rev = start.split()

469

user, rev = start.split()

468

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

470

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

469

return lines

471

return lines

470

472

471

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

473

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

472

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

474

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

473

"""checks style and portability of a given file

475

"""checks style and portability of a given file

474

476

475

:f: filepath

477

:f: filepath

476

:logfunc: function used to report error

478

:logfunc: function used to report error

477

logfunc(filename, linenumber, linecontent, errormessage)

479

logfunc(filename, linenumber, linecontent, errormessage)

478

:maxerr: number of error to display before aborting.

480

:maxerr: number of error to display before aborting.

479

Set to false (default) to report all errors

481

Set to false (default) to report all errors

480

482

481

return True if no error is found, False otherwise.

483

return True if no error is found, False otherwise.

482

"""

484

"""

483

blamecache = None

485

blamecache = None

484

result = True

486

result = True

485

487

486

try:

488

try:

487

fp = open(f)

489

fp = open(f)

488

except IOError as e:

490

except IOError as e:

489

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

491

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

490

return result

492

return result

491

pre = post = fp.read()

493

pre = post = fp.read()

492

fp.close()

494

fp.close()

493

495

494

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

496

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

495

if debug:

497

if debug:

496

print(name, f)

498

print(name, f)

497

fc = 0

499

fc = 0

498

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

500

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

499

if debug:

501

if debug:

500

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

502

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

501

name, match, f))

503

name, match, f))

502

continue

504

continue

503

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

505

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

504

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

506

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

505

# no- check- code

507

# no- check- code

506

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

508

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

507

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

509

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

508

# spelling, we write it with the expected spelling from

510

# spelling, we write it with the expected spelling from

509

# tests/test-check-code.t

511

# tests/test-check-code.t

510

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

512

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

511

return "Skip" # skip checking this file

513

return "Skip" # skip checking this file

512

for p, r in filters:

514

for p, r in filters:

513

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

515

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

514

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

516

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

515

if warnings:

517

if warnings:

516

pats = pats[0] + pats[1]

518

pats = pats[0] + pats[1]

517

else:

519

else:

518

pats = pats[0]

520

pats = pats[0]

519

# print post # uncomment to show filtered version

521

# print post # uncomment to show filtered version

520

522

521

if debug:

523

if debug:

522

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

524

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

523

525

524

prelines = None

526

prelines = None

525

errors = []

527

errors = []

526

for i, pat in enumerate(pats):

528

for i, pat in enumerate(pats):

527

if len(pat) == 3:

529

if len(pat) == 3:

528

p, msg, ignore = pat

530

p, msg, ignore = pat

529

else:

531

else:

530

p, msg = pat

532

p, msg = pat

531

ignore = None

533

ignore = None

532

if i >= nerrs:

534

if i >= nerrs:

533

msg = "warning: " + msg

535

msg = "warning: " + msg

534

536

535

pos = 0

537

pos = 0

536

n = 0

538

n = 0

537

for m in p.finditer(post):

539

for m in p.finditer(post):

538

if prelines is None:

540

if prelines is None:

539

prelines = pre.splitlines()

541

prelines = pre.splitlines()

540

postlines = post.splitlines(True)

542

postlines = post.splitlines(True)

541

543

542

start = m.start()

544

start = m.start()

543

while n < len(postlines):

545

while n < len(postlines):

544

step = len(postlines[n])

546

step = len(postlines[n])

545

if pos + step > start:

547

if pos + step > start:

546

break

548

break

547

pos += step

549

pos += step

548

n += 1

550

n += 1

549

l = prelines[n]

551

l = prelines[n]

550

552

551

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

553

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

552

if debug:

554

if debug:

553

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

555

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

554

name, f, n))

556

name, f, n))

555

continue

557

continue

556

bd = ""

558

bd = ""

557

if blame:

559

if blame:

558

bd = 'working directory'

560

bd = 'working directory'

559

if not blamecache:

561

if not blamecache:

560

blamecache = getblame(f)

562

blamecache = getblame(f)

561

if n < len(blamecache):

563

if n < len(blamecache):

562

bl, bu, br = blamecache[n]

564

bl, bu, br = blamecache[n]

563

if bl == l:

565

if bl == l:

564

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

566

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

565

567

566

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

568

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

567

result = False

569

result = False

568

570

569

errors.sort()

571

errors.sort()

570

for e in errors:

572

for e in errors:

571

logfunc(*e)

573

logfunc(*e)

572

fc += 1

574

fc += 1

573

if maxerr and fc >= maxerr:

575

if maxerr and fc >= maxerr:

574

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

576

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

575

break

577

break

576

578

577

return result

579

return result

578

580

579

if __name__ == "__main__":

581

if __name__ == "__main__":

580

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

582

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

581

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

583

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

582

help="include warning-level checks")

584

help="include warning-level checks")

583

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

585

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

584

help="max warnings per file")

586

help="max warnings per file")

585

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

587

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

586

help="use annotate to generate blame info")

588

help="use annotate to generate blame info")

587

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

589

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

588

help="show debug information")

590

help="show debug information")

589

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

591

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

590

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

592

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

591

593

592

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

594

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

593

lineno=True)

595

lineno=True)

594

(options, args) = parser.parse_args()

596

(options, args) = parser.parse_args()

595

597

596

if len(args) == 0:

598

if len(args) == 0:

597

check = glob.glob("*")

599

check = glob.glob("*")

598

else:

600

else:

599

check = args

601

check = args

600

602

601

ret = 0

603

ret = 0

602

for f in check:

604

for f in check:

603

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

605

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

604

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

606

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

605

lineno=options.lineno):

607

lineno=options.lineno):

606

ret = 1

608

ret = 1

607

sys.exit(ret)

609

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
             try:
                 import re2
             except ImportError:
                 re2 = None
             def compilere(pat, multiline=False):
                 if multiline:
                     pat = '(?m)' + pat
                 if re2:
                     try:
                         return re2.compile(pat)
                     except re2.error:
                         pass
                 return re.compile(pat)
             def repquote(m):
                 fromc = '.:'
                 tochr = 'pq'
                 def encodechr(i):
                     if i > 255:
                         return 'u'
                     c = chr(i)
                     if c in ' \n':
                         return c
                     if c.isalpha():
                         return 'x'
                     if c.isdigit():
                         return 'n'
                     try:
                         return tochr[fromc.find(c)]
                     except (ValueError, IndexError):
                         return 'o'
                 t = m.group('text')
                 tt = ''.join(encodechr(i) for i in xrange(256))
                 t = t.translate(tt)
                 return m.group('quote') + t + m.group('quote')
             def reppython(m):
                 comment = m.group('comment')
                 if comment:
                     l = len(comment.rstrip())
                     return "#" * l + comment[l:]
                 return repquote(m)
             def repcomment(m):
                 return m.group(1) + "#" * len(m.group(2))
             def repccomment(m):
                 t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
                 return m.group(1) + t + "*/"
             def repcallspaces(m):
                 t = re.sub(r"\n\s+", "\n", m.group(2))
                 return m.group(1) + t
             def repinclude(m):
                 return m.group(1) + "<foo>"
             def rephere(m):
                 t = re.sub(r"\S", "x", m.group(2))
                 return m.group(1) + t
             testpats = [
               [
                 (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),
                 (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
                 (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
                 (r'(?<!hg )grep.* -a', "don't use 'grep -a', use in-line python"),
                 (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
                 (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
                 (r'echo -n', "don't use 'echo -n', use printf"),
                 (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
                 (r'head -c', "don't use 'head -c', use 'dd'"),
                 (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
                 (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
                 (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
                 (r'printf.*[^\\]\\([1-9]|0\d)', "don't use 'printf \NNN', use Python"),
                 (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
                 (r'\$\(.*\)', "don't use $(expr), use `expr`"),
                 (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
                 (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
                  "use egrep for extended grep syntax"),
                 (r'/bin/', "don't use explicit paths for tools"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'export .*=', "don't export and assign at once"),
                 (r'^source\b', "don't use 'source', use '.'"),
                 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
                 (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
                 (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
                 (r'^stop\(\)', "don't use 'stop' as a shell function name"),
                 (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
                 (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
                 (r'^alias\b.*=', "don't use alias, use a function"),
                 (r'if\s*!', "don't use '!' to negate exit status"),
                 (r'/dev/u?random', "don't use entropy, use /dev/zero"),
                 (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
                 (r'^( *)\t', "don't use tabs to indent"),
                 (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
                  "put a backslash-escaped newline after sed 'i' command"),
                 (r'^diff *-\w*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
                 (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
                 (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'\|&', "don't use |&, use 2>&1"),
                 (r'\w =  +\w', "only one space after = allowed"),
                 (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
               ],
               # warnings
               [
                 (r'^function', "don't use 'function', use old style"),
                 (r'^diff.*-\w*N', "don't use 'diff -N'"),
                 (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
                 (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
                 (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
               ]
             ]
             testfilters = [
                 (r"( *)(#([^\n]*\S)?)", repcomment),
                 (r"<<(\S+)((.|\n)*?\n\1)", rephere),
             ]
             winglobmsg = "use (glob) to match Windows paths too"
             uprefix = r"^  \$ "
             utestpats = [
               [
                 (r'^(\S.*||  [$>] \S.*)[ \t]\n', "trailing whitespace on non-output"),
                 (uprefix + r'.*\|\s*sed[^|>\n]*\n',
                  "use regex test output patterns instead of sed"),
                 (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
                 (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
                 (uprefix + r'.*\|\| echo.*(fail|error)',
                  "explicit exit code checks unnecessary"),
                 (uprefix + r'set -e', "don't use set -e"),
                 (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
                 (uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "
                  "as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx
                  '# no-msys'), # in test-pull.t which is skipped on windows
                 (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
                 (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
                  winglobmsg),
                 (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
                  '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
                 (r'^  reverting (?!subrepo ).*/.*[^)]$', winglobmsg),
                 (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
                 (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
                 (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
                 (r'^  moving \S+/.*[^)]$', winglobmsg),
                 (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
                 (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
                 (r'^  .*file://\$TESTTMP',
                  'write "file:/*/$TESTTMP" + (glob) to match on windows too'),
                 (r'^  (cat|find): .*: No such file or directory',
                  'use test -f to test for file existence'),
                 (r'^  diff -[^ -]*p',
                  "don't use (external) diff with -p for portability"),
                 (r'^  [-+][-+][-+] .* [-+]0000 \(glob\)',
                  "glob timezone field in diff output for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',
                  "use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),
                 (r'^  @@ -[0-9]+ [+][0-9]+ @@',
                  "use '@@ -N* +N* @@ (glob)' style chunk header for portability"),
                 (uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'
                  r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',
                  "use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),
               ],
               # warnings
               [
                 (r'^  [^*?/\n]* \(glob\)$',
                  "glob match with no glob character (?*/)"),
               ]
             ]
             for i in [0, 1]:
                 for tp in testpats[i]:
                     p = tp[0]
                     m = tp[1]
                     if p.startswith(r'^'):
                         p = r"^  [$>] (%s)" % p[1:]
                     else:
                         p = r"^  [$>] .*(%s)" % p
                     utestpats[i].append((p, m) + tp[2:])
             utestfilters = [
                 (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
                 (r"( *)(#([^\n]*\S)?)", repcomment),
             ]
             pypats = [
               [
                 (r'^\s*def\s*\w+\s*\(.*,\s*\(',
                  "tuple parameter unpacking not available in Python 3+"),
                 (r'lambda\s*\(.*,.*\)',
                  "tuple parameter unpacking not available in Python 3+"),
                 (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
                 (r'\breduce\s*\(.*', "reduce is not available in Python 3+"),
                 (r'dict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
                  'dict-from-generator'),
                 (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
                 (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
                 (r'^\s*\t', "don't use tabs"),
                 (r'\S;\s*\n', "semicolon"),
                 (r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
                 (r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
                 (r'(\w|\)),\w', "missing whitespace after ,"),
                 (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
                 (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
                 (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'.{81}', "line too long"),
                 (r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
             #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
             #     "don't use underbars in identifiers"),
                 (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
                  "don't use camelcase in identifiers"),
                 (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
                  "linebreak after :"),
                 (r'class\s[^( \n]+:', "old-style class, use class foo(object)",
                  r'#.*old-style'),
                 (r'class\s[^( \n]+\(\):',
                  "class foo() creates old style object, use class foo(object)",
                  r'#.*old-style'),
                 (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                                         if k not in ('print', 'exec')),
                  "Python keyword is not a function"),
                 (r',]', "unneeded trailing ',' in list"),
             #    (r'class\s[A-Z][^\(]*\((?!Exception)',
             #     "don't capitalize non-exception classes"),
             #    (r'in range\(', "use xrange"),
             #    (r'^\s*print\s+', "avoid using print in core and extensions"),
                 (r'[\x80-\xff]', "non-ASCII character literal"),
                 (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
                 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
                  "gratuitous whitespace after Python keyword"),
                 (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
             #    (r'\s\s=', "gratuitous whitespace before ="),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
                  "missing whitespace around operator"),
                 (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
                  "missing whitespace around operator"),
                 (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
                  "wrong whitespace around ="),
                 (r'\([^()]*( =[^=]|[^<>!=]= )',
                  "no whitespace around = for named parameters"),
                 (r'raise Exception', "don't raise generic exceptions"),
                 (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
                  "don't use old-style two-argument raise, use Exception(message)"),
                 (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
                 (r' [=!]=\s+(True|False|None)',
                  "comparison with singleton, use 'is' or 'is not' instead"),
                 (r'^\s*(while|if) [01]:',
                  "use True/False for constant Boolean expression"),
                 (r'(?:(?<!def)\s+|\()hasattr',
                  'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
                 (r'opener\([^)]*\).read\(',
                  "use opener.read() instead"),
                 (r'opener\([^)]*\).write\(',
                  "use opener.write() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.read\(',
                  "use util.readfile() instead"),
                 (r'[\s\(](open|file)\([^)]*\)\.write\(',
                  "use util.writefile() instead"),
                 (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'[\s\(](open|file)\([^)]*\)\.',
                  "always assign an opened file to a variable, and close it afterwards"),
                 (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
                 (r'\.debug\(\_', "don't mark debug messages for translation"),
                 (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
                 (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
                 (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
                  'legacy exception syntax; use "as" instead of ","'),
                 (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
                 (r'ui\.(status|progress|write|note|warn)\([\'\"]x',
                  "missing _() in ui message (use () to hide false-positives)"),
                 (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
                 (r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
                 (r'os\.path\.join\(.*, *(""|\'\')\)',
                  "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
                 (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
                 # XXX only catch mutable arguments on the first line of the definition
                 (r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),
                 (r'\butil\.Abort\b', "directly use error.Abort"),
                 (r'^import Queue', "don't use Queue, use util.queue + util.empty"),
+                (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),
+                (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
               ],
               # warnings
               [
                 (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
               ]
             ]
             pyfilters = [
                 (r"""(?msx)(?P<comment>\#.*?$)|
                      ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
                       (?P<text>(([^\\]|\\.)*?))
                       (?P=quote))""", reppython),
             ]
             txtfilters = []
             txtpats = [
               [
                 ('\s$', 'trailing whitespace'),
                 ('.. note::[ \n][^\n]', 'add two newlines after note::')
               ],
               []
             ]
             cpats = [
               [
                 (r'//', "don't use //-style comments"),
                 (r'^  ', "don't use spaces to indent"),
                 (r'\S\t', "don't use tabs except for indent"),
                 (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
                 (r'.{81}', "line too long"),
                 (r'(while|if|do|for)\(', "use space after while/if/do/for"),
                 (r'return\(', "return is not a function"),
                 (r' ;', "no space before ;"),
                 (r'[^;] \)', "no space before )"),
                 (r'[)][{]', "space between ) and {"),
                 (r'\w+\* \w+', "use int *foo, not int* foo"),
                 (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
                 (r'\w+ (\+\+|--)', "use foo++, not foo ++"),
                 (r'\w,\w', "missing whitespace after ,"),
                 (r'^[^#]\w[+/*]\w', "missing whitespace in expression"),
                 (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
                 (r'^#\s+\w', "use #foo, not # foo"),
                 (r'[^\n]\Z', "no trailing newline"),
                 (r'^\s*#import\b', "use only #include in standard C code"),
                 (r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),
                 (r'strcat\(', "don't use strcat"),
               ],
               # warnings
               []
             ]
             cfilters = [
                 (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
                 (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
                 (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
                 (r'(\()([^)]+\))', repcallspaces),
             ]
             inutilpats = [
               [
                 (r'\bui\.', "don't use ui in util"),
               ],
               # warnings
               []
             ]
             inrevlogpats = [
               [
                 (r'\brepo\.', "don't use repo in revlog"),
               ],
               # warnings
               []
             ]
             webtemplatefilters = []
             webtemplatepats = [
               [],
               [
                 (r'{desc(\|(?!websub|firstline)[^\|]*)+}',
                  'follow desc keyword with either firstline or websub'),
               ]
             ]
             checks = [
                 ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
                 ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),
                 ('c', r'.*\.[ch]$', '', cfilters, cpats),
                 ('unified test', r'.*\.t$', '', utestfilters, utestpats),
                 ('layering violation repo in revlog', r'mercurial/revlog\.py', '',
                  pyfilters, inrevlogpats),
                 ('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,
                  inutilpats),
                 ('txt', r'.*\.txt$', '', txtfilters, txtpats),
                 ('web template', r'mercurial/templates/.*\.tmpl', '',
                  webtemplatefilters, webtemplatepats),
             ]
             def _preparepats():
                 for c in checks:
                     failandwarn = c[-1]
                     for pats in failandwarn:
                         for i, pseq in enumerate(pats):
                             # fix-up regexes for multi-line searches
                             p = pseq[0]
                             # \s doesn't match \n
                             p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
                             # [^...] doesn't match newline
                             p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)
                             pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]
                     filters = c[3]
                     for i, flt in enumerate(filters):
                         filters[i] = re.compile(flt[0]), flt[1]
             _preparepats()
             class norepeatlogger(object):
                 def __init__(self):
                     self._lastseen = None
                 def log(self, fname, lineno, line, msg, blame):
                     """print error related a to given line of a given file.
                     The faulty line will also be printed but only once in the case
                     of multiple errors.
                     :fname: filename
                     :lineno: line number
                     :line: actual content of the line
                     :msg: error message
                     """
                     msgid = fname, lineno, line
                     if msgid != self._lastseen:
                         if blame:
                             print("%s:%d (%s):" % (fname, lineno, blame))
                         else:
                             print("%s:%d:" % (fname, lineno))
                         print(" > %s" % line)
                         self._lastseen = msgid
                     print(" " + msg)
             _defaultlogger = norepeatlogger()
             def getblame(f):
                 lines = []
                 for l in os.popen('hg annotate -un %s' % f):
                     start, line = l.split(':', 1)
                     user, rev = start.split()
                     lines.append((line[1:-1], user, rev))
                 return lines
             def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,
                           blame=False, debug=False, lineno=True):
                 """checks style and portability of a given file
                 :f: filepath
                 :logfunc: function used to report error
                           logfunc(filename, linenumber, linecontent, errormessage)
                 :maxerr: number of error to display before aborting.
                          Set to false (default) to report all errors
                 return True if no error is found, False otherwise.
                 """
                 blamecache = None
                 result = True
                 try:
                     fp = open(f)
                 except IOError as e:
                     print("Skipping %s, %s" % (f, str(e).split(':', 1)[0]))
                     return result
                 pre = post = fp.read()
                 fp.close()
                 for name, match, magic, filters, pats in checks:
                     if debug:
                         print(name, f)
                     fc = 0
                     if not (re.match(match, f) or (magic and re.search(magic, pre))):
                         if debug:
                             print("Skipping %s for %s it doesn't match %s" % (
                                    name, match, f))
                         continue
                     if "no-" "check-code" in pre:
                         # If you're looking at this line, it's because a file has:
                         # no- check- code
                         # but the reason to output skipping is to make life for
                         # tests easier. So, instead of writing it with a normal
                         # spelling, we write it with the expected spelling from
                         # tests/test-check-code.t
                         print("Skipping %s it has no-che?k-code (glob)" % f)
                         return "Skip" # skip checking this file
                     for p, r in filters:
                         post = re.sub(p, r, post)
                     nerrs = len(pats[0]) # nerr elements are errors
                     if warnings:
                         pats = pats[0] + pats[1]
                     else:
                         pats = pats[0]
                     # print post # uncomment to show filtered version
                     if debug:
                         print("Checking %s for %s" % (name, f))
                     prelines = None
                     errors = []
                     for i, pat in enumerate(pats):
                         if len(pat) == 3:
                             p, msg, ignore = pat
                         else:
                             p, msg = pat
                             ignore = None
                         if i >= nerrs:
                             msg = "warning: " + msg
                         pos = 0
                         n = 0
                         for m in p.finditer(post):
                             if prelines is None:
                                 prelines = pre.splitlines()
                                 postlines = post.splitlines(True)
                             start = m.start()
                             while n < len(postlines):
                                 step = len(postlines[n])
                                 if pos + step > start:
                                     break
                                 pos += step
                                 n += 1
                             l = prelines[n]
                             if ignore and re.search(ignore, l, re.MULTILINE):
                                 if debug:
                                     print("Skipping %s for %s:%s (ignore pattern)" % (
                                         name, f, n))
                                 continue
                             bd = ""
                             if blame:
                                 bd = 'working directory'
                                 if not blamecache:
                                     blamecache = getblame(f)
                                 if n < len(blamecache):
                                     bl, bu, br = blamecache[n]
                                     if bl == l:
                                         bd = '%s@%s' % (bu, br)
                             errors.append((f, lineno and n + 1, l, msg, bd))
                             result = False
                     errors.sort()
                     for e in errors:
                         logfunc(*e)
                         fc += 1
                         if maxerr and fc >= maxerr:
                             print(" (too many errors, giving up)")
                             break
                 return result
             if __name__ == "__main__":
                 parser = optparse.OptionParser("%prog [options] [files]")
                 parser.add_option("-w", "--warnings", action="store_true",
                                   help="include warning-level checks")
                 parser.add_option("-p", "--per-file", type="int",
                                   help="max warnings per file")
                 parser.add_option("-b", "--blame", action="store_true",
                                   help="use annotate to generate blame info")
                 parser.add_option("", "--debug", action="store_true",
                                   help="show debug information")
                 parser.add_option("", "--nolineno", action="store_false",
                                   dest='lineno', help="don't show line numbers")
                 parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                                     lineno=True)
                 (options, args) = parser.parse_args()
                 if len(args) == 0:
                     check = glob.glob("*")
                 else:
                     check = args
                 ret = 0
                 for f in check:
                     if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                                      blame=options.blame, debug=options.debug,
                                      lineno=options.lineno):
                         ret = 1
                 sys.exit(ret)