mercurial-scm/hg-stable: contrib/check-code.py comparison

comparison contrib/check-code.py @ 15281:aeeb2afcdc25 stable

check-code: support multiline matches like try/except/finally - match one pattern at a time against entire file - find line containing match - sort matches by line number

author	Matt Mackall <mpm@selenic.com>
date	Sun, 16 Oct 2011 20:26:20 -0500
parents	5a0fdc715769
children	ebeac9c41456

comparison

equal deleted inserted replaced

-:52bc0c4daaf9
+:aeeb2afcdc25
 import keyword
 import optparse
 def repquote(m):
 t = re.sub(r"\w", "x", m.group('text'))
-t = re.sub(r"[^\sx]", "o", t)
+t = re.sub(r"[^\s\nx]", "o", t)
 return m.group('quote') + t + m.group('quote')
 def reppython(m):
 comment = m.group('comment')
 if comment:
 testpats = [
 [
 (r'(pushd|popd)', "don't use 'pushd' or 'popd', use 'cd'"),
-(r'\W\$?\(\([^\)]*\)\)', "don't use (()) or $(()), use 'expr'"),
+(r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
 (r'^function', "don't use 'function', use old style"),
 (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
 (r'echo.*\\n', "don't use 'echo \\n', use printf"),
 (r'echo -n', "don't use 'echo -n', use printf"),
 (r'^diff.*-\w*N', "don't use 'diff -N'"),
-(r'(^| )wc[^|]*$', "filter wc output"),
+(r'(^| )wc[^|\n]*$', "filter wc output"),
 (r'head -c', "don't use 'head -c', use 'dd'"),
 (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
 (r'printf.*\\\d\d\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',
+(r'(^|\|\s*)grep (-\w\s+)*[^|\n]*[(|]\w',
 "use egrep for extended grep syntax"),
 (r'/bin/', "don't use explicit paths for tools"),
 (r'\$PWD', "don't use $PWD, use `pwd`"),
 (r'[^\n]\Z', "no trailing newline"),
 (r'export.*=', "don't export and assign at once"),
-('^([^"\']|("[^"]*")|(\'[^\']*\'))*\\^', "^ must be quoted"),
+('^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\\^', "^ must be quoted"),
 (r'^source\b', "don't use 'source', use '.'"),
 (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
-(r'ls\s+[^|-]+\s+-', "options to 'ls' must come before filenames"),
+(r'ls\s+[^|\n-]+\s+-', "options to 'ls' must come before filenames"),
-(r'[^>]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
+(r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
 (r'stop\(\)', "don't use 'stop' as a shell function name"),
 ],
 # warnings
 []
 ]
 uprefix = r"^  \$ "
 uprefixc = r"^  > "
 utestpats = [
 [
-(r'^(\S|  $ ).*(\S\s+|^\s+)\n', "trailing whitespace on non-output"),
+(r'^(\S|  $ ).*(\S[ \t]+|^[ \t]+)\n', "trailing whitespace on non-output"),
 (uprefix + r'.*\|\s*sed', "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"),
 (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
 (r'^\s*\t', "don't use tabs"),
 (r'\S;\s*\n', "semicolon"),
 (r'\w,\w', "missing whitespace after ,"),
 (r'\w[+/*\-<>]\w', "missing whitespace in expression"),
-(r'^\s+\w+=\w+[^,)]$', "missing whitespace in assignment"),
+(r'^\s+\w+=\w+[^,)\n]$', "missing whitespace in assignment"),
+(r'(?m)(\s+)try:\n((?:\n|\1\s.*\n)+?)\1except.*?:\n'
+r'((?:\n|\1\s.*\n)+?)\1finally:', 'no try/except/finally in Py2.4'),
 (r'.{85}', "line too long"),
 (r'[^\n]\Z', "no trailing newline"),
-(r'(\S\s+|^\s+)\n', "trailing whitespace"),
+(r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
-#    (r'^\s+[^_ ][^_. ]+_[^_]+\s*=', "don't use underbars in identifiers"),
+#    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=', "don't use underbars in identifiers"),
 #    (r'\w*[a-z][A-Z]\w*\s*=', "don't use camelcase in identifiers"),
-(r'^\s*(if|while|def|class|except|try)\s[^[]*:\s*[^\]#\s]+',
+(r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
 "linebreak after :"),
-(r'class\s[^( ]+:', "old-style class, use class foo(object)"),
+(r'class\s[^( \n]+:', "old-style class, use class foo(object)"),
-(r'class\s[^( ]+\(\):',
+(r'class\s[^( \n]+\(\):',
 "class foo() not available in Python 2.4, use class foo(object)"),
 (r'\b(%s)\(' % '|'.join(keyword.kwlist),
 "Python keyword is not a function"),
 (r',]', "unneeded trailing ',' in list"),
 #    (r'class\s[A-Z][^\(]*\((?!Exception)',
 (r'(?<!def)\s+(callable)\(',
 "callable not available in Python 3, use getattr(f, '__call__', None)"),
 (r'if\s.*\selse', "if ... else form not available in Python 2.4"),
 (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
 "gratuitous whitespace after Python keyword"),
-(r'([\(\[]\s\S)|(\S\s[\)\]])', "gratuitous whitespace in () or []"),
+(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"),
 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\s+|^\s+)\n', "trailing whitespace"),
+(r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
 (r'.{85}', "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'\w+\* \w+', "use int *foo, not int* foo"),
 if warnings:
 pats = pats[0] + pats[1]
 else:
 pats = pats[0]
 # print post # uncomment to show filtered version
-z = enumerate(zip(pre.splitlines(), post.splitlines(True)))
 if debug:
 print "Checking %s for %s" % (name, f)
-for n, l in z:
-if "check-code" + "-ignore" in l[0]:
+prelines = None
-if debug:
+errors = []
-print "Skipping %s for %s:%s (check-code -ignore)" % (
+for p, msg in pats:
-name, f, n)
+pos = 0
-continue
+n = 0
-for p, msg in pats:
+for m in re.finditer(p, post):
-if re.search(p, l[1]):
+if prelines is None:
-bd = ""
+prelines = pre.splitlines()
-if blame:
+postlines = post.splitlines(True)
-bd = 'working directory'
-if not blamecache:
+start = m.start()
-blamecache = getblame(f)
+while n < len(postlines):
-if n < len(blamecache):
+step = len(postlines[n])
-bl, bu, br = blamecache[n]
+if pos + step > start:
-if bl == l[0]:
+break
-bd = '%s@%s' % (bu, br)
+pos += step
-logfunc(f, n + 1, l[0], msg, bd)
+n += 1
-fc += 1
+l = prelines[n]
-result = False
+if "check-code" + "-ignore" in l:
+if debug:
+print "Skipping %s for %s:%s (check-code -ignore)" % (
+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, n + 1, l, msg, bd))
+result = False
+errors.sort()
+for e in errors:
+logfunc(*e)
+fc += 1
 if maxerr is not None 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",

Mercurial > public > mercurial-scm > hg-stable

comparison contrib/check-code.py @ 15281:aeeb2afcdc25 stable