# This file is part of A Boneless Datastructure Language # Copyright (C) 2020 Soni L. # # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU Affero General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU Affero General Public License for more details. # # You should have received a copy of the GNU Affero General Public License # along with this program. If not, see . """[Internal] pyparsing-based Parser. Provides `BUILT_SYNTAX`. """ from pyparsing import Suppress, Literal, Forward, CharsNotIn, StringEnd from pyparsing import Combine, Optional, Group, Word, srange, Empty from abdl import exceptions as exc from abdl import _vm def _err_str_esc(match_str, pos, toks): raise exc.PatternError("Error in string escape", pos=pos, toks=toks) def _err_str_end(match_str, pos, toks): raise exc.PatternError("Unfinished string", pos=pos, toks=toks) def _err_re_esc(match_str, pos, toks): raise exc.PatternError("Error in regex escape", pos=pos, toks=toks) def _err_re_end(match_str, pos, toks): raise exc.PatternError("Unfinished regex", pos=pos, toks=toks) def _err_tok(match_str, pos, toks): raise exc.PatternError("Unexpected token", pos=pos, toks=toks) def _build_syntax(): # pylint: disable=too-many-locals subtree = Forward() skippable = Optional("?", default="") escape_char = Literal("%") any_char = CharsNotIn("", exact=1) str_token = Literal("'") re_token = Literal("/") unexpected_token = any_char.copy().setParseAction(_err_tok) unexpected_end = StringEnd().setParseAction(_err_tok) # TODO reformat these unexpected_str_escape = any_char.copy().setParseAction(_err_str_esc) str_escape = Suppress(escape_char) + (str_token | escape_char) str_escape |= escape_char + unexpected_str_escape str_char = (str_escape | CharsNotIn("%'")) str_literal = (Combine(Suppress(str_token) + str_char[...] + (Suppress(str_token) | StringEnd().setParseAction(_err_str_end))) + skippable) str_literal.setParseAction(_vm.StringKey.action) unexpected_re_escape = any_char.copy().setParseAction(_err_re_esc) re_escape = Suppress(escape_char) + (re_token | escape_char) re_escape |= escape_char + unexpected_re_escape re_char = (re_escape | CharsNotIn("%/")) re_literal = (Combine(Suppress(re_token) + re_char[...] + (Suppress(re_token) | StringEnd().setParseAction(_err_re_end))) + skippable) re_literal.setParseAction(_vm.RegexKey.action) arrow = Literal("->") arrow.setParseAction(_vm.Arrow.action) identifier = Word(srange("[A-Za-z_]"), srange("[A-Za-z0-9_]")) identifier.setParseAction(_vm.Ident.action) parameter = (Suppress("$") + skippable + identifier) parameter.setParseAction(_vm.Param.action) type_ = (Suppress(":") + skippable + Suppress("$") + identifier) type_.setParseAction(_vm.ApplyPredicate.action) # support for objects-as-keys keysubtree = (Suppress("[") + Group(type_[...] + subtree) + (Suppress("]") | unexpected_token | unexpected_end) + skippable) keysubtree.setParseAction(_vm.KeySubtree.action) # represents key matching - switches from "key" to "value" tag = ((identifier + Optional(parameter | str_literal | re_literal | keysubtree) | parameter | str_literal | re_literal | keysubtree) + type_[...] + Empty().setParseAction(_vm.End.action)) # multiple value matching valuesubtree = (Suppress("(") + Group(type_[...] + subtree) + (Suppress(")") | unexpected_token | unexpected_end) + Optional("?", default="")) valuesubtree.setParseAction(_vm.ValueSubtree.action) # arrow and tag, value subtree subtree <<= ((arrow + tag)[...] + (valuesubtree + Empty().setParseAction(_vm.End.action))[...]) return ((subtree | unexpected_token) + (StringEnd() | unexpected_token)).parseWithTabs() BUILT_SYNTAX = _build_syntax()