# 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 (

    encoding,

    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 _brepr(obj):

    if isinstance(obj, bytes):

        return b"'%s'" % stringutil.escapestr(obj)

    return encoding.strtolocal(repr(obj))

def _prettyformat(tree, leafnodes, level, lines):

    if not isinstance(tree, tuple):

        lines.append((level, _brepr(tree)))

    elif tree[0] in leafnodes:

        rs = map(_brepr, 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