gitmirror/lark/tools/standalone.py

###{standalone
#
#
#   Lark Stand-alone Generator Tool
# ----------------------------------
# Generates a stand-alone LALR(1) parser with a standard lexer
#
# Git:    https://github.com/erezsh/lark
# Author: Erez Shinan (erezshin@gmail.com)
#
#
#    >>> LICENSE
#
#    This tool and its generated code use a separate license from Lark.
#
#    It is licensed under GPLv2 or above.
#
#    If you wish to purchase a commercial license for this tool and its
#    generated code, contact me via email.
#
#    If GPL is incompatible with your free or open-source project,
#    contact me and we'll work it out (for free).
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation, either version 2 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 General Public License for more details.
#
#    See <http://www.gnu.org/licenses/>.
#
#

import os
from io import open
###}

import pprint
import codecs
import sys
import os
from pprint import pprint
from os import path
from collections import defaultdict

import lark
from lark import Lark
from lark.parsers.lalr_analysis import Reduce


from lark.grammar import RuleOptions, Rule
from lark.lexer import TerminalDef

_dir = path.dirname(__file__)
_larkdir = path.join(_dir, path.pardir)


EXTRACT_STANDALONE_FILES = [
    'tools/standalone.py',
    'exceptions.py',
    'utils.py',
    'tree.py',
    'visitors.py',
    'indenter.py',
    'grammar.py',
    'lexer.py',
    'common.py',
    'parse_tree_builder.py',
    'parsers/lalr_parser.py',
    'parsers/lalr_analysis.py',
    'parser_frontends.py',
    'lark.py',
]

def extract_sections(lines):
    section = None
    text = []
    sections = defaultdict(list)
    for l in lines:
        if l.startswith('###'):
            if l[3] == '{':
                section = l[4:].strip()
            elif l[3] == '}':
                sections[section] += text
                section = None
                text = []
            else:
                raise ValueError(l)
        elif section:
            text.append(l)

    return {name:''.join(text) for name, text in sections.items()}


def main(fobj, start):
    lark_inst = Lark(fobj, parser="lalr", lexer="contextual", start=start)

    print('# The file was automatically generated by Lark v%s' % lark.__version__)

    for pyfile in EXTRACT_STANDALONE_FILES:
        with open(os.path.join(_larkdir, pyfile)) as f:
            print (extract_sections(f)['standalone'])

    data, m = lark_inst.memo_serialize([TerminalDef, Rule])
    print( 'DATA = (' )
    # pprint(data, width=160)
    print(data)
    print(')')
    print( 'MEMO = (')
    print(m)
    print(')')


    print('Shift = 0')
    print('Reduce = 1')
    print("def Lark_StandAlone(transformer=None, postlex=None):")
    print("  namespace = {'Rule': Rule, 'TerminalDef': TerminalDef}")
    print("  return Lark.deserialize(DATA, namespace, MEMO, transformer=transformer, postlex=postlex)")



if __name__ == '__main__':
    if len(sys.argv) < 2:
        print("Lark Stand-alone Generator Tool")
        print("Usage: python -m lark.tools.standalone <grammar-file> [<start>]")
        sys.exit(1)

    if len(sys.argv) == 3:
        fn, start = sys.argv[1:]
    elif len(sys.argv) == 2:
        fn, start = sys.argv[1], 'start'
    else:
        assert False, sys.argv

    with codecs.open(fn, encoding='utf8') as f:
        main(f, start)