view mercurial/parser.py @ 13750:7eb82f88e157

# User Dan Villiom Podlaski Christiansen <[e-mail]>
# Date 1289564504 -3600
# Node ID b75264c15cc888cf38c3c7b8f619801e3c2589c7
# Parent  89b2e5d940f669e590096c6be70eee61c9172fff
revsets: overload the branch() revset to also take a branch name.

This should only change semantics in the specific case of a tag/branch
conflict where the tag wasn't done on the branch with the same
name. Previously, branch(whatever) would resolve to the branch of the
tag in that case, whereas now it will resolve to the branch of the
name. The previous behaviour, while documented, seemed very
counter-intuitive to me.

An alternate approach would be to introduce a new revset such as
branchname() or namedbranch(). While this would retain backwards
compatibility, the distinction between it and branch() would not be
readily apparent to users. The most intuitive behaviour would be to
have branch(x) require 'x' to be a branch name, and something like
branchof(x) or samebranch(x) do what branch(x) currently
does. Unfortunately, our backwards compatibility guarantees prevent us
from doing that.

Please note that while 'hg tag' guards against shadowing a branch, 'hg
branch' does not. Besides, even if it did, that wouldn't solve the
issue of conversions with such tags and branches...

# parser.py - simple top-down operator precedence parser for mercurial
#
# Copyright 2010 Matt Mackall <[e-mail]>
#
# 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 pairs
# elements is a mapping of types to binding strength, prefix and infix actions
# an action is a tree node name, a tree label, and an optional match
# __call__(program) parses program into a labelled tree

import error

class parser(object):
    def __init__(self, tokenizer, elements, methods=None):
        self._tokenizer = tokenizer
        self._elements = elements
        self._methods = methods
        self.current = None
    def _advance(self):
        'advance the tokenizer'
        t = self.current
        try:
            self.current = self._iter.next()
        except StopIteration:
            pass
        return t
    def _match(self, m, pos):
        '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 _parse(self, bind=0):
        token, value, pos = self._advance()
        # handle prefix rules on current token
        prefix = self._elements[token][1]
        if not prefix:
            raise error.ParseError("not a prefix: %s" % token, pos)
        if len(prefix) == 1:
            expr = (prefix[0], value)
        else:
            if len(prefix) > 2 and prefix[2] == self.current[0]:
                self._match(prefix[2], pos)
                expr = (prefix[0], None)
            else:
                expr = (prefix[0], self._parse(prefix[1]))
                if len(prefix) > 2:
                    self._match(prefix[2], pos)
        # gather tokens until we meet a lower binding strength
        while bind < self._elements[self.current[0]][0]:
            token, value, pos = self._advance()
            e = self._elements[token]
            # check for suffix - next token isn't a valid prefix
            if len(e) == 4 and not self._elements[self.current[0]][1]:
                suffix = e[3]
                expr = (suffix[0], expr)
            else:
                # handle infix rules
                if len(e) < 3 or not e[2]:
                    raise error.ParseError("not an infix: %s" % token, pos)
                infix = e[2]
                if len(infix) == 3 and infix[2] == self.current[0]:
                    self._match(infix[2], pos)
                    expr = (infix[0], expr, (None))
                else:
                    expr = (infix[0], expr, self._parse(infix[1]))
                    if len(infix) == 3:
                        self._match(infix[2], pos)
        return expr
    def parse(self, message):
        'generate a parse tree from a message'
        self._iter = self._tokenizer(message)
        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, message):
        'parse a message into a parse tree and evaluate if methods given'
        t = self.parse(message)
        if self._methods:
            return self.eval(t)
        return t