mercurial/parser.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Wed, 27 Mar 2019 18:35:59 +0100
changeset 42044 bb271ec2fbfb
parent 39050 0a2ce5b43574
child 42232 29798c9ba5c9
permissions -rw-r--r--
compression: introduce a `storage.revlog.zstd.level` configuration This option control the zstd compression level used when compressing revlog chunk. The usage of zstd for revlog compression has not graduated from experimental yet, but we intend to fix that soon. The option name for the compression level is more straight forward to pick, so this changesets comes first. Having a dedicated option for each compression engine is useful because they don't support the same range of values. I ran the same measurement as for the zlib compression level (in the parent changesets). The variation in repository size is stay mostly in the same (small) range. The "read/write" performance see smallish variation, but are overall much better than zlib. Write performance show the same tend of having better write performance for when reaching high-end compression. Again, we don't intend to change the default zstd compression level (currently: 3) in this series. However this is worth investigating in the future. The Performance comparison of zlib vs zstd is quite impressive. The repository size stay in the same range, but the performance are much better in all situations. Comparison summary ================== We are looking at: - performance range for zlib - performance range for zstd - comparison of default zstd (level-3) to default zlib (level 6) - comparison of the slowest zstd time to the fastest zlib time Read performance: ----------------- | zlib | zstd | cmp | f2s mercurial | 0.170159 - 0.189219 | 0.144127 - 0.149624 | 80% | 88% pypy | 2.679217 - 2.768691 | 1.532317 - 1.705044 | 60% | 63% netbeans | 122.477027 - 141.620281 | 72.996346 - 89.731560 | 58% | 73% mozilla | 147.867662 - 170.572118 | 91.700995 - 105.853099 | 56% | 71% Write performance: ------------------ | zlib | zstd | cmp | f2s mercurial | 53.250304 - 56.2936129 | 40.877025 - 45.677286 | 75% | 86% pypy | 460.721984 - 476.589918 | 270.545409 - 301.002219 | 63% | 65% netbeans | 520.560316 - 715.930400 | 370.356311 - 428.329652 | 55% | 82% mozilla | 739.803002 - 987.056093 | 505.152906 - 591.930683 | 57% | 80% Raw data -------- repo alg lvl .hg/store size 00manifest.d read write mercurial zlib 1 49,402,813 5,963,475 0.170159 53.250304 mercurial zlib 6 47,197,397 5,875,730 0.182820 56.264320 mercurial zlib 9 47,121,596 5,849,781 0.189219 56.293612 mercurial zstd 1 49,737,084 5,966,355 0.144127 40.877025 mercurial zstd 3 48,961,867 5,895,208 0.146376 42.268142 mercurial zstd 5 48,200,592 5,938,676 0.149624 43.162875 mercurial zstd 10 47,833,520 5,913,353 0.145185 44.012489 mercurial zstd 15 47,314,604 5,728,679 0.147686 45.677286 mercurial zstd 20 47,330,502 5,830,539 0.145789 45.025407 mercurial zstd 22 47,330,076 5,830,539 0.143996 44.690460 pypy zlib 1 370,830,572 28,462,425 2.679217 460.721984 pypy zlib 6 340,112,317 27,648,747 2.768691 467.537158 pypy zlib 9 338,360,736 27,639,003 2.763495 476.589918 pypy zstd 1 362,377,479 27,916,214 1.532317 270.545409 pypy zstd 3 354,137,693 27,905,988 1.686718 294.951509 pypy zstd 5 342,640,043 27,655,774 1.705044 301.002219 pypy zstd 10 334,224,327 27,164,493 1.567287 285.186239 pypy zstd 15 329,000,363 26,645,965 1.637729 299.561332 pypy zstd 20 324,534,039 26,199,547 1.526813 302.149827 pypy zstd 22 324,530,595 26,198,932 1.525718 307.821218 netbeans zlib 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans zlib 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans zlib 9 1,197,135,671 155,034,586 141.620281 678.297064 netbeans zstd 1 1,259,581,737 160,840,613 72.996346 370.356311 netbeans zstd 3 1,232,978,122 157,691,551 81.622317 396.733087 netbeans zstd 5 1,208,034,075 160,246,880 83.080549 364.342626 netbeans zstd 10 1,188,624,176 156,083,417 79.323935 403.594602 netbeans zstd 15 1,176,973,589 153,859,477 89.731560 428.329652 netbeans zstd 20 1,162,958,258 151,147,535 82.842667 392.335349 netbeans zstd 22 1,162,707,029 151,150,220 82.565695 402.840655 mozilla zlib 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla zlib 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla zlib 9 2,587,542,494 287,018,264 163.622338 739.803002 mozilla zstd 1 2,723,159,348 286,617,532 91.700995 570.042751 mozilla zstd 3 2,665,055,001 286,152,013 95.240155 561.412805 mozilla zstd 5 2,607,819,817 288,060,030 101.978048 505.152906 mozilla zstd 10 2,558,761,085 283,967,648 104.113481 497.771202 mozilla zstd 15 2,526,216,060 275,581,300 105.853099 591.930683 mozilla zstd 20 2,485,114,806 266,478,859 95.268795 576.515389 mozilla zstd 22 2,484,869,080 266,456,505 94.429282 572.785537

# parser.py - simple top-down operator precedence parser 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.

# see http://effbot.org/zone/simple-top-down-parsing.htm and
# http://eli.thegreenplace.net/2010/01/02/top-down-operator-precedence-parsing/
# for background

# takes a tokenizer and elements
# tokenizer is an iterator that returns (type, value, pos) tuples
# elements is a mapping of types to binding strength, primary, prefix, infix
# and suffix actions
# an action is a tree node name, a tree label, and an optional match
# __call__(program) parses program into a labeled tree

from __future__ import absolute_import, print_function

from .i18n import _
from . import (
    error,
    pycompat,
    util,
)
from .utils import (
    stringutil,
)

class parser(object):
    def __init__(self, elements, methods=None):
        self._elements = elements
        self._methods = methods
        self.current = None
    def _advance(self):
        'advance the tokenizer'
        t = self.current
        self.current = next(self._iter, None)
        return t
    def _hasnewterm(self):
        'True if next token may start new term'
        return any(self._elements[self.current[0]][1:3])
    def _match(self, m):
        'make sure the tokenizer matches an end condition'
        if self.current[0] != m:
            raise error.ParseError(_("unexpected token: %s") % self.current[0],
                                   self.current[2])
        self._advance()
    def _parseoperand(self, bind, m=None):
        'gather right-hand-side operand until an end condition or binding met'
        if m and self.current[0] == m:
            expr = None
        else:
            expr = self._parse(bind)
        if m:
            self._match(m)
        return expr
    def _parse(self, bind=0):
        token, value, pos = self._advance()
        # handle prefix rules on current token, take as primary if unambiguous
        primary, prefix = self._elements[token][1:3]
        if primary and not (prefix and self._hasnewterm()):
            expr = (primary, value)
        elif prefix:
            expr = (prefix[0], self._parseoperand(*prefix[1:]))
        else:
            raise error.ParseError(_("not a prefix: %s") % token, pos)
        # gather tokens until we meet a lower binding strength
        while bind < self._elements[self.current[0]][0]:
            token, value, pos = self._advance()
            # handle infix rules, take as suffix if unambiguous
            infix, suffix = self._elements[token][3:]
            if suffix and not (infix and self._hasnewterm()):
                expr = (suffix, expr)
            elif infix:
                expr = (infix[0], expr, self._parseoperand(*infix[1:]))
            else:
                raise error.ParseError(_("not an infix: %s") % token, pos)
        return expr
    def parse(self, tokeniter):
        'generate a parse tree from tokens'
        self._iter = tokeniter
        self._advance()
        res = self._parse()
        token, value, pos = self.current
        return res, pos
    def eval(self, tree):
        'recursively evaluate a parse tree using node methods'
        if not isinstance(tree, tuple):
            return tree
        return self._methods[tree[0]](*[self.eval(t) for t in tree[1:]])
    def __call__(self, tokeniter):
        'parse tokens into a parse tree and evaluate if methods given'
        t = self.parse(tokeniter)
        if self._methods:
            return self.eval(t)
        return t

def splitargspec(spec):
    """Parse spec of function arguments into (poskeys, varkey, keys, optkey)

    >>> splitargspec(b'')
    ([], None, [], None)
    >>> splitargspec(b'foo bar')
    ([], None, ['foo', 'bar'], None)
    >>> splitargspec(b'foo *bar baz **qux')
    (['foo'], 'bar', ['baz'], 'qux')
    >>> splitargspec(b'*foo')
    ([], 'foo', [], None)
    >>> splitargspec(b'**foo')
    ([], None, [], 'foo')
    """
    optkey = None
    pre, sep, post = spec.partition('**')
    if sep:
        posts = post.split()
        if not posts:
            raise error.ProgrammingError('no **optkey name provided')
        if len(posts) > 1:
            raise error.ProgrammingError('excessive **optkey names provided')
        optkey = posts[0]

    pre, sep, post = pre.partition('*')
    pres = pre.split()
    posts = post.split()
    if sep:
        if not posts:
            raise error.ProgrammingError('no *varkey name provided')
        return pres, posts[0], posts[1:], optkey
    return [], None, pres, optkey

def buildargsdict(trees, funcname, argspec, keyvaluenode, keynode):
    """Build dict from list containing positional and keyword arguments

    Arguments are specified by a tuple of ``(poskeys, varkey, keys, optkey)``
    where

    - ``poskeys``: list of names of positional arguments
    - ``varkey``: optional argument name that takes up remainder
    - ``keys``: list of names that can be either positional or keyword arguments
    - ``optkey``: optional argument name that takes up excess keyword arguments

    If ``varkey`` specified, all ``keys`` must be given as keyword arguments.

    Invalid keywords, too few positional arguments, or too many positional
    arguments are rejected, but missing keyword arguments are just omitted.
    """
    poskeys, varkey, keys, optkey = argspec
    kwstart = next((i for i, x in enumerate(trees) if x[0] == keyvaluenode),
                   len(trees))
    if kwstart < len(poskeys):
        raise error.ParseError(_("%(func)s takes at least %(nargs)d positional "
                                 "arguments")
                               % {'func': funcname, 'nargs': len(poskeys)})
    if not varkey and kwstart > len(poskeys) + len(keys):
        raise error.ParseError(_("%(func)s takes at most %(nargs)d positional "
                                 "arguments")
                               % {'func': funcname,
                                  'nargs': len(poskeys) + len(keys)})
    args = util.sortdict()
    # consume positional arguments
    for k, x in zip(poskeys, trees[:kwstart]):
        args[k] = x
    if varkey:
        args[varkey] = trees[len(args):kwstart]
    else:
        for k, x in zip(keys, trees[len(args):kwstart]):
            args[k] = x
    # remainder should be keyword arguments
    if optkey:
        args[optkey] = util.sortdict()
    for x in trees[kwstart:]:
        if x[0] != keyvaluenode or x[1][0] != keynode:
            raise error.ParseError(_("%(func)s got an invalid argument")
                                   % {'func': funcname})
        k = x[1][1]
        if k in keys:
            d = args
        elif not optkey:
            raise error.ParseError(_("%(func)s got an unexpected keyword "
                                     "argument '%(key)s'")
                                   % {'func': funcname, 'key': k})
        else:
            d = args[optkey]
        if k in d:
            raise error.ParseError(_("%(func)s got multiple values for keyword "
                                     "argument '%(key)s'")
                                   % {'func': funcname, 'key': k})
        d[k] = x[2]
    return args

def unescapestr(s):
    try:
        return stringutil.unescapestr(s)
    except ValueError as e:
        # mangle Python's exception into our format
        raise error.ParseError(pycompat.bytestr(e).lower())

def _prettyformat(tree, leafnodes, level, lines):
    if not isinstance(tree, tuple):
        lines.append((level, stringutil.pprint(tree)))
    elif tree[0] in leafnodes:
        rs = map(stringutil.pprint, tree[1:])
        lines.append((level, '(%s %s)' % (tree[0], ' '.join(rs))))
    else:
        lines.append((level, '(%s' % tree[0]))
        for s in tree[1:]:
            _prettyformat(s, leafnodes, level + 1, lines)
        lines[-1:] = [(lines[-1][0], lines[-1][1] + ')')]

def prettyformat(tree, leafnodes):
    lines = []
    _prettyformat(tree, leafnodes, 0, lines)
    output = '\n'.join(('  ' * l + s) for l, s in lines)
    return output

def simplifyinfixops(tree, targetnodes):
    """Flatten chained infix operations to reduce usage of Python stack

    >>> from . import pycompat
    >>> def f(tree):
    ...     s = prettyformat(simplifyinfixops(tree, (b'or',)), (b'symbol',))
    ...     print(pycompat.sysstr(s))
    >>> f((b'or',
    ...     (b'or',
    ...       (b'symbol', b'1'),
    ...       (b'symbol', b'2')),
    ...     (b'symbol', b'3')))
    (or
      (symbol '1')
      (symbol '2')
      (symbol '3'))
    >>> f((b'func',
    ...     (b'symbol', b'p1'),
    ...     (b'or',
    ...       (b'or',
    ...         (b'func',
    ...           (b'symbol', b'sort'),
    ...           (b'list',
    ...             (b'or',
    ...               (b'or',
    ...                 (b'symbol', b'1'),
    ...                 (b'symbol', b'2')),
    ...               (b'symbol', b'3')),
    ...             (b'negate',
    ...               (b'symbol', b'rev')))),
    ...         (b'and',
    ...           (b'symbol', b'4'),
    ...           (b'group',
    ...             (b'or',
    ...               (b'or',
    ...                 (b'symbol', b'5'),
    ...                 (b'symbol', b'6')),
    ...               (b'symbol', b'7'))))),
    ...       (b'symbol', b'8'))))
    (func
      (symbol 'p1')
      (or
        (func
          (symbol 'sort')
          (list
            (or
              (symbol '1')
              (symbol '2')
              (symbol '3'))
            (negate
              (symbol 'rev'))))
        (and
          (symbol '4')
          (group
            (or
              (symbol '5')
              (symbol '6')
              (symbol '7'))))
        (symbol '8')))
    """
    if not isinstance(tree, tuple):
        return tree
    op = tree[0]
    if op not in targetnodes:
        return (op,) + tuple(simplifyinfixops(x, targetnodes) for x in tree[1:])

    # walk down left nodes taking each right node. no recursion to left nodes
    # because infix operators are left-associative, i.e. left tree is deep.
    # e.g. '1 + 2 + 3' -> (+ (+ 1 2) 3) -> (+ 1 2 3)
    simplified = []
    x = tree
    while x[0] == op:
        l, r = x[1:]
        simplified.append(simplifyinfixops(r, targetnodes))
        x = l
    simplified.append(simplifyinfixops(x, targetnodes))
    simplified.append(op)
    return tuple(reversed(simplified))

def _buildtree(template, placeholder, replstack):
    if template == placeholder:
        return replstack.pop()
    if not isinstance(template, tuple):
        return template
    return tuple(_buildtree(x, placeholder, replstack) for x in template)

def buildtree(template, placeholder, *repls):
    """Create new tree by substituting placeholders by replacements

    >>> _ = (b'symbol', b'_')
    >>> def f(template, *repls):
    ...     return buildtree(template, _, *repls)
    >>> f((b'func', (b'symbol', b'only'), (b'list', _, _)),
    ...   ('symbol', '1'), ('symbol', '2'))
    ('func', ('symbol', 'only'), ('list', ('symbol', '1'), ('symbol', '2')))
    >>> f((b'and', _, (b'not', _)), (b'symbol', b'1'), (b'symbol', b'2'))
    ('and', ('symbol', '1'), ('not', ('symbol', '2')))
    """
    if not isinstance(placeholder, tuple):
        raise error.ProgrammingError('placeholder must be a node tuple')
    replstack = list(reversed(repls))
    r = _buildtree(template, placeholder, replstack)
    if replstack:
        raise error.ProgrammingError('too many replacements')
    return r

def _matchtree(pattern, tree, placeholder, incompletenodes, matches):
    if pattern == tree:
        return True
    if not isinstance(pattern, tuple) or not isinstance(tree, tuple):
        return False
    if pattern == placeholder and tree[0] not in incompletenodes:
        matches.append(tree)
        return True
    if len(pattern) != len(tree):
        return False
    return all(_matchtree(p, x, placeholder, incompletenodes, matches)
               for p, x in zip(pattern, tree))

def matchtree(pattern, tree, placeholder=None, incompletenodes=()):
    """If a tree matches the pattern, return a list of the tree and nodes
    matched with the placeholder; Otherwise None

    >>> def f(pattern, tree):
    ...     m = matchtree(pattern, tree, _, {b'keyvalue', b'list'})
    ...     if m:
    ...         return m[1:]

    >>> _ = (b'symbol', b'_')
    >>> f((b'func', (b'symbol', b'ancestors'), _),
    ...   (b'func', (b'symbol', b'ancestors'), (b'symbol', b'1')))
    [('symbol', '1')]
    >>> f((b'func', (b'symbol', b'ancestors'), _),
    ...   (b'func', (b'symbol', b'ancestors'), None))
    >>> f((b'range', (b'dagrange', _, _), _),
    ...   (b'range',
    ...     (b'dagrange', (b'symbol', b'1'), (b'symbol', b'2')),
    ...     (b'symbol', b'3')))
    [('symbol', '1'), ('symbol', '2'), ('symbol', '3')]

    The placeholder does not match the specified incomplete nodes because
    an incomplete node (e.g. argument list) cannot construct an expression.

    >>> f((b'func', (b'symbol', b'ancestors'), _),
    ...   (b'func', (b'symbol', b'ancestors'),
    ...     (b'list', (b'symbol', b'1'), (b'symbol', b'2'))))

    The placeholder may be omitted, but which shouldn't match a None node.

    >>> _ = None
    >>> f((b'func', (b'symbol', b'ancestors'), None),
    ...   (b'func', (b'symbol', b'ancestors'), (b'symbol', b'0')))
    """
    if placeholder is not None and not isinstance(placeholder, tuple):
        raise error.ProgrammingError('placeholder must be a node tuple')
    matches = [tree]
    if _matchtree(pattern, tree, placeholder, incompletenodes, matches):
        return matches

def parseerrordetail(inst):
    """Compose error message from specified ParseError object
    """
    if len(inst.args) > 1:
        return _('at %d: %s') % (inst.args[1], inst.args[0])
    else:
        return inst.args[0]

class alias(object):
    """Parsed result of alias"""

    def __init__(self, name, args, err, replacement):
        self.name = name
        self.args = args
        self.error = err
        self.replacement = replacement
        # whether own `error` information is already shown or not.
        # this avoids showing same warning multiple times at each
        # `expandaliases`.
        self.warned = False

class basealiasrules(object):
    """Parsing and expansion rule set of aliases

    This is a helper for fileset/revset/template aliases. A concrete rule set
    should be made by sub-classing this and implementing class/static methods.

    It supports alias expansion of symbol and function-call styles::

        # decl = defn
        h = heads(default)
        b($1) = ancestors($1) - ancestors(default)
    """
    # typically a config section, which will be included in error messages
    _section = None
    # tag of symbol node
    _symbolnode = 'symbol'

    def __new__(cls):
        raise TypeError("'%s' is not instantiatable" % cls.__name__)

    @staticmethod
    def _parse(spec):
        """Parse an alias name, arguments and definition"""
        raise NotImplementedError

    @staticmethod
    def _trygetfunc(tree):
        """Return (name, args) if tree is a function; otherwise None"""
        raise NotImplementedError

    @classmethod
    def _builddecl(cls, decl):
        """Parse an alias declaration into ``(name, args, errorstr)``

        This function analyzes the parsed tree. The parsing rule is provided
        by ``_parse()``.

        - ``name``: of declared alias (may be ``decl`` itself at error)
        - ``args``: list of argument names (or None for symbol declaration)
        - ``errorstr``: detail about detected error (or None)

        >>> sym = lambda x: (b'symbol', x)
        >>> symlist = lambda *xs: (b'list',) + tuple(sym(x) for x in xs)
        >>> func = lambda n, a: (b'func', sym(n), a)
        >>> parsemap = {
        ...     b'foo': sym(b'foo'),
        ...     b'$foo': sym(b'$foo'),
        ...     b'foo::bar': (b'dagrange', sym(b'foo'), sym(b'bar')),
        ...     b'foo()': func(b'foo', None),
        ...     b'$foo()': func(b'$foo', None),
        ...     b'foo($1, $2)': func(b'foo', symlist(b'$1', b'$2')),
        ...     b'foo(bar_bar, baz.baz)':
        ...         func(b'foo', symlist(b'bar_bar', b'baz.baz')),
        ...     b'foo(bar($1, $2))':
        ...         func(b'foo', func(b'bar', symlist(b'$1', b'$2'))),
        ...     b'foo($1, $2, nested($1, $2))':
        ...         func(b'foo', (symlist(b'$1', b'$2') +
        ...                      (func(b'nested', symlist(b'$1', b'$2')),))),
        ...     b'foo("bar")': func(b'foo', (b'string', b'bar')),
        ...     b'foo($1, $2': error.ParseError(b'unexpected token: end', 10),
        ...     b'foo("bar': error.ParseError(b'unterminated string', 5),
        ...     b'foo($1, $2, $1)': func(b'foo', symlist(b'$1', b'$2', b'$1')),
        ... }
        >>> def parse(expr):
        ...     x = parsemap[expr]
        ...     if isinstance(x, Exception):
        ...         raise x
        ...     return x
        >>> def trygetfunc(tree):
        ...     if not tree or tree[0] != b'func' or tree[1][0] != b'symbol':
        ...         return None
        ...     if not tree[2]:
        ...         return tree[1][1], []
        ...     if tree[2][0] == b'list':
        ...         return tree[1][1], list(tree[2][1:])
        ...     return tree[1][1], [tree[2]]
        >>> class aliasrules(basealiasrules):
        ...     _parse = staticmethod(parse)
        ...     _trygetfunc = staticmethod(trygetfunc)
        >>> builddecl = aliasrules._builddecl
        >>> builddecl(b'foo')
        ('foo', None, None)
        >>> builddecl(b'$foo')
        ('$foo', None, "invalid symbol '$foo'")
        >>> builddecl(b'foo::bar')
        ('foo::bar', None, 'invalid format')
        >>> builddecl(b'foo()')
        ('foo', [], None)
        >>> builddecl(b'$foo()')
        ('$foo()', None, "invalid function '$foo'")
        >>> builddecl(b'foo($1, $2)')
        ('foo', ['$1', '$2'], None)
        >>> builddecl(b'foo(bar_bar, baz.baz)')
        ('foo', ['bar_bar', 'baz.baz'], None)
        >>> builddecl(b'foo($1, $2, nested($1, $2))')
        ('foo($1, $2, nested($1, $2))', None, 'invalid argument list')
        >>> builddecl(b'foo(bar($1, $2))')
        ('foo(bar($1, $2))', None, 'invalid argument list')
        >>> builddecl(b'foo("bar")')
        ('foo("bar")', None, 'invalid argument list')
        >>> builddecl(b'foo($1, $2')
        ('foo($1, $2', None, 'at 10: unexpected token: end')
        >>> builddecl(b'foo("bar')
        ('foo("bar', None, 'at 5: unterminated string')
        >>> builddecl(b'foo($1, $2, $1)')
        ('foo', None, 'argument names collide with each other')
        """
        try:
            tree = cls._parse(decl)
        except error.ParseError as inst:
            return (decl, None, parseerrordetail(inst))

        if tree[0] == cls._symbolnode:
            # "name = ...." style
            name = tree[1]
            if name.startswith('$'):
                return (decl, None, _("invalid symbol '%s'") % name)
            return (name, None, None)

        func = cls._trygetfunc(tree)
        if func:
            # "name(arg, ....) = ...." style
            name, args = func
            if name.startswith('$'):
                return (decl, None, _("invalid function '%s'") % name)
            if any(t[0] != cls._symbolnode for t in args):
                return (decl, None, _("invalid argument list"))
            if len(args) != len(set(args)):
                return (name, None, _("argument names collide with each other"))
            return (name, [t[1] for t in args], None)

        return (decl, None, _("invalid format"))

    @classmethod
    def _relabelargs(cls, tree, args):
        """Mark alias arguments as ``_aliasarg``"""
        if not isinstance(tree, tuple):
            return tree
        op = tree[0]
        if op != cls._symbolnode:
            return (op,) + tuple(cls._relabelargs(x, args) for x in tree[1:])

        assert len(tree) == 2
        sym = tree[1]
        if sym in args:
            op = '_aliasarg'
        elif sym.startswith('$'):
            raise error.ParseError(_("invalid symbol '%s'") % sym)
        return (op, sym)

    @classmethod
    def _builddefn(cls, defn, args):
        """Parse an alias definition into a tree and marks substitutions

        This function marks alias argument references as ``_aliasarg``. The
        parsing rule is provided by ``_parse()``.

        ``args`` is a list of alias argument names, or None if the alias
        is declared as a symbol.

        >>> from . import pycompat
        >>> parsemap = {
        ...     b'$1 or foo': (b'or', (b'symbol', b'$1'), (b'symbol', b'foo')),
        ...     b'$1 or $bar':
        ...         (b'or', (b'symbol', b'$1'), (b'symbol', b'$bar')),
        ...     b'$10 or baz':
        ...         (b'or', (b'symbol', b'$10'), (b'symbol', b'baz')),
        ...     b'"$1" or "foo"':
        ...         (b'or', (b'string', b'$1'), (b'string', b'foo')),
        ... }
        >>> class aliasrules(basealiasrules):
        ...     _parse = staticmethod(parsemap.__getitem__)
        ...     _trygetfunc = staticmethod(lambda x: None)
        >>> builddefn = aliasrules._builddefn
        >>> def pprint(tree):
        ...     s = prettyformat(tree, (b'_aliasarg', b'string', b'symbol'))
        ...     print(pycompat.sysstr(s))
        >>> args = [b'$1', b'$2', b'foo']
        >>> pprint(builddefn(b'$1 or foo', args))
        (or
          (_aliasarg '$1')
          (_aliasarg 'foo'))
        >>> try:
        ...     builddefn(b'$1 or $bar', args)
        ... except error.ParseError as inst:
        ...     print(pycompat.sysstr(parseerrordetail(inst)))
        invalid symbol '$bar'
        >>> args = [b'$1', b'$10', b'foo']
        >>> pprint(builddefn(b'$10 or baz', args))
        (or
          (_aliasarg '$10')
          (symbol 'baz'))
        >>> pprint(builddefn(b'"$1" or "foo"', args))
        (or
          (string '$1')
          (string 'foo'))
        """
        tree = cls._parse(defn)
        if args:
            args = set(args)
        else:
            args = set()
        return cls._relabelargs(tree, args)

    @classmethod
    def build(cls, decl, defn):
        """Parse an alias declaration and definition into an alias object"""
        repl = efmt = None
        name, args, err = cls._builddecl(decl)
        if err:
            efmt = _('bad declaration of %(section)s "%(name)s": %(error)s')
        else:
            try:
                repl = cls._builddefn(defn, args)
            except error.ParseError as inst:
                err = parseerrordetail(inst)
                efmt = _('bad definition of %(section)s "%(name)s": %(error)s')
        if err:
            err = efmt % {'section': cls._section, 'name': name, 'error': err}
        return alias(name, args, err, repl)

    @classmethod
    def buildmap(cls, items):
        """Parse a list of alias (name, replacement) pairs into a dict of
        alias objects"""
        aliases = {}
        for decl, defn in items:
            a = cls.build(decl, defn)
            aliases[a.name] = a
        return aliases

    @classmethod
    def _getalias(cls, aliases, tree):
        """If tree looks like an unexpanded alias, return (alias, pattern-args)
        pair. Return None otherwise.
        """
        if not isinstance(tree, tuple):
            return None
        if tree[0] == cls._symbolnode:
            name = tree[1]
            a = aliases.get(name)
            if a and a.args is None:
                return a, None
        func = cls._trygetfunc(tree)
        if func:
            name, args = func
            a = aliases.get(name)
            if a and a.args is not None:
                return a, args
        return None

    @classmethod
    def _expandargs(cls, tree, args):
        """Replace _aliasarg instances with the substitution value of the
        same name in args, recursively.
        """
        if not isinstance(tree, tuple):
            return tree
        if tree[0] == '_aliasarg':
            sym = tree[1]
            return args[sym]
        return tuple(cls._expandargs(t, args) for t in tree)

    @classmethod
    def _expand(cls, aliases, tree, expanding, cache):
        if not isinstance(tree, tuple):
            return tree
        r = cls._getalias(aliases, tree)
        if r is None:
            return tuple(cls._expand(aliases, t, expanding, cache)
                         for t in tree)
        a, l = r
        if a.error:
            raise error.Abort(a.error)
        if a in expanding:
            raise error.ParseError(_('infinite expansion of %(section)s '
                                     '"%(name)s" detected')
                                   % {'section': cls._section, 'name': a.name})
        # get cacheable replacement tree by expanding aliases recursively
        expanding.append(a)
        if a.name not in cache:
            cache[a.name] = cls._expand(aliases, a.replacement, expanding,
                                        cache)
        result = cache[a.name]
        expanding.pop()
        if a.args is None:
            return result
        # substitute function arguments in replacement tree
        if len(l) != len(a.args):
            raise error.ParseError(_('invalid number of arguments: %d')
                                   % len(l))
        l = [cls._expand(aliases, t, [], cache) for t in l]
        return cls._expandargs(result, dict(zip(a.args, l)))

    @classmethod
    def expand(cls, aliases, tree):
        """Expand aliases in tree, recursively.

        'aliases' is a dictionary mapping user defined aliases to alias objects.
        """
        return cls._expand(aliases, tree, [], {})