Mercurial > hg
view mercurial/parser.py @ 14077:c285bdb0572a
util.url: copy urllib.unquote() into util to improve startup times
The ui class uses util.hasscheme() in a couple of places, causing hg
to import urllib even when it doesn't need to. This copies
urllib.unquote() to avoid that import.
perfstartup time before the URL refactoring (8796fb6af67e):
! wall 0.050692 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)
before this change:
! wall 0.064742 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)
after this change:
! wall 0.052126 comb 0.000000 user 0.000000 sys 0.000000 (best of 100
author | Brodie Rao <brodie@bitheap.org> |
---|---|
date | Sat, 30 Apr 2011 09:43:23 -0700 |
parents | e798e430c5e5 |
children | 4b93bd041772 |
line wrap: on
line source
# 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 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