comparison contrib/check-code.py @ 29278:5eda83fb09fc

check-code: centralize rules depending on implementation of repquote

This decreases the cost of checking which regexp should be adjusted at
change of repquote().

29277:79a11506803f

        except re2.error:
            pass
    return re.compile(pat)

def repquote(m):
    fixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q'}
    def encodechr(i):
        if i > 255:
            return 'u'
        c = chr(i)

    (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+[xpqo][\'"]\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* = ',

    (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"'),

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

pyfilters = [

    (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),

29278:5eda83fb09fc

        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'}
    def encodechr(i):
        if i > 255:
            return 'u'
        c = chr(i)

    (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* = ',

    (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"'),

    (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][\'"]\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'^#\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),