#!/usr/bin/env python3

#

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

#

# Copyright 2010 Olivia Mackall <olivia@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

"""

import glob

import keyword

import optparse

import os

import re

import sys

if sys.version_info[0] < 3:

    opentext = open

else:

    def opentext(f):

        return open(f, encoding='latin1')

try:

    xrange

except NameError:

    xrange = range

try:

    import re2

except ImportError:

    re2 = None

import testparseutil

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)

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

# patterns (especially pypats), before changing around repquote()

_repquotefixedmap = {

    ' ': ' ',

    '\n': '\n',

    '.': 'p',

    ':': 'q',

    '%': '%',

    '\\': 'b',

    '*': 'A',

    '+': 'P',

    '-': 'M',

}

def _repquoteencodechr(i):

    if i > 255:

        return 'u'

    c = chr(i)

    if c in _repquotefixedmap:

        return _repquotefixedmap[c]

    if c.isalpha():

        return 'x'

    if c.isdigit():

        return 'n'

    return 'o'

_repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))

def repquote(m):

    t = m.group('text')

    t = t.translate(_repquotett)

    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'\b(push|pop)d\b', "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'\bls\b.*-\w*R', "don't use 'ls -R', use 'find'"),

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

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

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

        (

            r'\[[^\]]+==',

            '[ foo == bar ] is a bashism, use [ foo = bar ] instead',

        ),

        (r'(^|\|\s*)egrep', "use grep -E for extended grep syntax"),

        (r'(^|\|\s*)fgrep', "use grep -F for fixed string grepping"),

        (r'(^|\|\s*)e?grep .*\\S', "don't use \\S in regular expression"),

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

        (r'#!.*/bash', "don't use bash in shebang, use sh"),

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

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

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

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

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

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

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

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

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

        (

            r'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'[\s="`\']python\s(?!bindings)', "don't use 'python', use '$PYTHON'"),

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

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

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

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

        (

            r'\bsed\b.*[^\\]\\n',

            "don't use 'sed ... \\n', use a \\ and a newline",

        ),

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

        (r'cp.* -r ', "don't use 'cp -r', use 'cp -R'"),

        (r'grep.* -[ABC]', "don't use grep's context flags"),

        (

            r'find.*-printf',

            "don't use 'find -printf', it doesn't exist on BSD find(1)",

        ),

        (r'\$RANDOM ', "don't use bash-only $RANDOM to generate random values"),

    ],

    # 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`", "no-pwd-check"),

        (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),

]

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'.*\|\| 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+:\.|' '# no-msys',  # -Rxxx

        ),  # in test-pull.t which is skipped on windows

        (

            r'^  [^$>].*27\.0\.0\.1',

            'use $LOCALIP not an explicit loopback address',

        ),

        (

            r'^  (?![>$] ).*\$LOCALIP.*[^)]$',

            'mark $LOCALIP output lines with (glob) to help tests in BSD jails',

        ),

        (

            r'^  (cat|find): .*: \$ENOENT\$',

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

        ),

        (

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

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

        ),

        (r' readlink ', 'use readlink.py instead of readlink'),

        (

            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'^  (?!.*\$LOCALIP)[^*?/\n]* \(glob\)$',

            "glob match with no glob string (?, *, /, and $LOCALIP)",

        ),

    ],

]

# transform plain test rules to unified test's

for i in [0, 1]:

    for tp in testpats[i]:

        p = tp[0]

        m = tp[1]

        if p.startswith('^'):

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

        else:

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

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

# don't transform the following rules:

# "  > \t" and "  \t" should be allowed in unified tests

testpats[0].append((r'^( *)\t', "don't use tabs to indent"))

utestpats[0].append((r'^( ?)\t', "don't use tabs to indent"))

utestfilters = [

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

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

]

# common patterns to check *.py

commonpypats = [

    [

        (r'\\$', 'Use () to wrap long lines in Python, not \\'),

        (

            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'\bdict\(.*=',

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

        (

            (

                # a line ending with a colon, potentially with trailing comments

                r':([ \t]*#[^\n]*)?\n'

                # one that is not a pass and not only a comment

                r'(?P<indent>[ \t]+)[^#][^\n]+\n'

                # more lines at the same indent level

                r'((?P=indent)[^\n]+\n)*'

                # a pass at the same indent level, which is bogus

                r'(?P=indent)pass[ \t\n#]'

            ),

            'omit superfluous pass',

        ),

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

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

        (

            r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',

            "linebreak after :",

        ),

        (

            r'\b(%s)\('

            % '|'.join(k for k in keyword.kwlist if k not in ('print', 'exec')),

            "Python keyword is not a function",

        ),

        #    (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'([\(\[][ \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'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'^\s*if False(:| +and)', 'Remove code instead of using `if False`'),

        (r'opener\([^)]*\).read\(', "use opener.read() instead"),

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

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

        (r'\bdef\s+__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