#!/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.

import re, glob, os, sys

import keyword

import optparse

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):

    t = re.sub(r"\w", "x", m.group('text'))

    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:

        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'(^| )wc[^|]*$\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'^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"),

  ],

  # 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.*||  [$>] .*)[ \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"),

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

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

     winglobmsg),

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

    (r'^  reverting .*/.*[^)]$', winglobmsg, '\$TESTTMP/unix-repo$'),

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

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

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

     '\$TESTTMP/unix-repo$'),

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

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

     winglobmsg, '\$TESTTMP/unix-repo$'),

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

     winglobmsg, '\$TESTTMP/unix-repo$'),

  ],

  # warnings

  [

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

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

  ]

]

for i in [0, 1]:

    for p, m in testpats[i]:

        if p.startswith(r'^'):

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

        else:

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

        utestpats[i].append((p, m))

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'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',

     '2to3 can\'t always rewrite "import qux, foo.bar", '

     'use "import foo.bar" on its own line instead.'),

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

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

    (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'[^_]_\("[^"]+"\s*%', "don't use % inside _()"),

    (r"[^_]_\('[^']+'\s*%", "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'(\s+)try:\n((?:\n|\1\s.*\n)+?)\1except.*?:\n'

     r'((?:\n|\1\s.*\n)+?)\1finally:', 'no try/except/finally in Python 2.4'),

    (r'(?<!def)(\s+|^|\()next\(.+\)',

     'no next(foo) in Python 2.4 and 2.5, use foo.next() instead'),

    (r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?'

     r'((?:\n|\1\s.*\n)+?)\1finally:',

     'no yield inside try/finally in Python 2.4'),

    (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'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)',

#     "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() not available in Python 2.4"),

    (r'^\s*with\s+', "with not available in Python 2.4"),

    (r'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"),

    (r'^\s*except.* as .*:', "except as not available in Python 2.4"),

    (r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"),

    (r'(?<!def)\s+(any|all|format)\(',

     "any/all/format not available in Python 2.4"),

    (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'([\(\[][ \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'BaseException', 'not in Python 2.4, use Exception'),

    (r'os\.path\.relpath', 'os.path.relpath is not in Python 2.5'),

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

     "use opener.write() instead"),

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

     "use util.readfile() instead"),

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

     "use util.readfile() 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)descendent', "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':\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"),

  ],

  # warnings

  [

  ]

]

pyfilters = [

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

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

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

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

]

txtfilters = []

txtpats = [

  [

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

  ],

  []

]

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'[)][{]', "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'^#\s+\w', "use #foo, not # foo"),

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

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

  ],

  # 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

  []

]

checks = [

    ('python', r'.*\.(py|cgi)$', 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),

]

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[2]

        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)